diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 0fa47ddf4c46..f7ac0e663976 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -597,7 +597,18 @@
 			placement constraint by the physical address range of
 			memory allocations. A value of 0 disables CMA
 			altogether. For more information, see
-			include/linux/dma-contiguous.h
+			kernel/dma/contiguous.c
+
+	cma_pernuma=nn[MG]
+			[ARM64,KNL]
+			Sets the size of kernel per-numa memory area for
+			contiguous memory allocations. A value of 0 disables
+			per-numa CMA altogether. And If this option is not
+			specificed, the default value is 0.
+			With per-numa CMA enabled, DMA users on node nid will
+			first try to allocate buffer from the pernuma area
+			which is located in node nid, if the allocation fails,
+			they will fallback to the global default memory area.
 
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 3b3abbbb4b9a..ea0413276ddb 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -516,48 +516,56 @@ routines, e.g.:::
 	}
 
 
-Part II - Advanced dma usage
-----------------------------
+Part II - Non-coherent DMA allocations
+--------------------------------------
 
-Warning: These pieces of the DMA API should not be used in the
-majority of cases, since they cater for unlikely corner cases that
-don't belong in usual drivers.
+These APIs allow to allocate pages in the kernel direct mapping that are
+guaranteed to be DMA addressable.  This means that unlike dma_alloc_coherent,
+virt_to_page can be called on the resulting address, and the resulting
+struct page can be used for everything a struct page is suitable for.
 
-If you don't understand how cache line coherency works between a
-processor and an I/O device, you should not be using this part of the
-API at all.
+If you don't understand how cache line coherency works between a processor and
+an I/O device, you should not be using this part of the API.
 
 ::
 
 	void *
-	dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-			gfp_t flag, unsigned long attrs)
+	dma_alloc_noncoherent(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp)
 
-Identical to dma_alloc_coherent() except that when the
-DMA_ATTR_NON_CONSISTENT flags is passed in the attrs argument, the
-platform will choose to return either consistent or non-consistent memory
-as it sees fit.  By using this API, you are guaranteeing to the platform
-that you have all the correct and necessary sync points for this memory
-in the driver should it choose to return non-consistent memory.
+This routine allocates a region of <size> bytes of consistent memory.  It
+returns a pointer to the allocated region (in the processor's virtual address
+space) or NULL if the allocation failed.  The returned memory may or may not
+be in the kernels direct mapping.  Drivers must not call virt_to_page on
+the returned memory region.
 
-Note: where the platform can return consistent memory, it will
-guarantee that the sync points become nops.
+It also returns a <dma_handle> which may be cast to an unsigned integer the
+same width as the bus and given to the device as the DMA address base of
+the region.
 
-Warning:  Handling non-consistent memory is a real pain.  You should
-only use this API if you positively know your driver will be
-required to work on one of the rare (usually non-PCI) architectures
-that simply cannot make consistent memory.
+The dir parameter specified if data is read and/or written by the device,
+see dma_map_single() for details.
+
+The gfp parameter allows the caller to specify the ``GFP_`` flags (see
+kmalloc()) for the allocation, but rejects flags used to specify a memory
+zone such as GFP_DMA or GFP_HIGHMEM.
+
+Before giving the memory to the device, dma_sync_single_for_device() needs
+to be called, and before reading memory written by the device,
+dma_sync_single_for_cpu(), just like for streaming DMA mappings that are
+reused.
 
 ::
 
 	void
-	dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-		       dma_addr_t dma_handle, unsigned long attrs)
+	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
+			dma_addr_t dma_handle, enum dma_data_direction dir)
 
-Free memory allocated by the dma_alloc_attrs().  All common
-parameters must be identical to those otherwise passed to dma_free_coherent,
-and the attrs argument must be identical to the attrs passed to
-dma_alloc_attrs().
+Free a region of memory previously allocated using dma_alloc_noncoherent().
+dev, size and dma_handle and dir must all be the same as those passed into
+dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
+the dma_alloc_noncoherent().
 
 ::
 
@@ -575,41 +583,6 @@ memory or doing partial flushes.
 	into the width returned by this call.  It will also always be a power
 	of two for easy alignment.
 
-::
-
-	void
-	dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		       enum dma_data_direction direction)
-
-Do a partial sync of memory that was allocated by dma_alloc_attrs() with
-the DMA_ATTR_NON_CONSISTENT flag starting at virtual address vaddr and
-continuing on for size.  Again, you *must* observe the cache line
-boundaries when doing this.
-
-::
-
-	int
-	dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				    dma_addr_t device_addr, size_t size);
-
-Declare region of memory to be handed out by dma_alloc_coherent() when
-it's asked for coherent memory for this device.
-
-phys_addr is the CPU physical address to which the memory is currently
-assigned (this will be ioremapped so the CPU can access the region).
-
-device_addr is the DMA address the device needs to be programmed
-with to actually address this memory (this will be handed out as the
-dma_addr_t in dma_alloc_coherent()).
-
-size is the size of the area (must be multiples of PAGE_SIZE).
-
-As a simplification for the platforms, only *one* such region of
-memory may be declared per device.
-
-For reasons of efficiency, most platforms choose to track the declared
-region only at the granularity of a page.  For smaller allocations,
-you should use the dma_pool() API.
 
 Part III - Debug drivers use of the DMA-API
 -------------------------------------------
diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 29dcbe8826e8..1887d92e8e92 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -25,14 +25,6 @@ Since it is optional for platforms to implement DMA_ATTR_WRITE_COMBINE,
 those that do not will simply ignore the attribute and exhibit default
 behavior.
 
-DMA_ATTR_NON_CONSISTENT
------------------------
-
-DMA_ATTR_NON_CONSISTENT lets the platform to choose to return either
-consistent or non-consistent memory as it sees fit.  By using this API,
-you are guaranteeing to the platform that you have all the correct and
-necessary sync points for this memory in the driver.
-
 DMA_ATTR_NO_KERNEL_MAPPING
 --------------------------
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 42fd3e3a252c..0f39d1ca7770 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5216,7 +5216,7 @@ T:	git git://git.infradead.org/users/hch/dma-mapping.git
 F:	include/asm-generic/dma-mapping.h
 F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
-F:	include/linux/dma-noncoherent.h
+F:	include/linux/dma-map-ops.h
 F:	kernel/dma/
 
 DMA-BUF HEAPS FRAMEWORK
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 81037907268d..d84b19aa8e9d 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -11,7 +11,7 @@
 #include <linux/export.h>
 #include <linux/scatterlist.h>
 #include <linux/log2.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu-helper.h>
 
 #include <asm/io.h>
@@ -141,12 +141,7 @@ iommu_arena_find_pages(struct device *dev, struct pci_iommu_arena *arena,
 	unsigned long boundary_size;
 
 	base = arena->dma_base >> PAGE_SHIFT;
-	if (dev) {
-		boundary_size = dma_get_seg_boundary(dev) + 1;
-		boundary_size >>= PAGE_SHIFT;
-	} else {
-		boundary_size = 1UL << (32 - PAGE_SHIFT);
-	}
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	/* Search forward for the first mask-aligned sequence of N free ptes */
 	ptes = arena->ptes;
@@ -957,5 +952,7 @@ const struct dma_map_ops alpha_pci_ops = {
 	.dma_supported		= alpha_pci_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(alpha_pci_ops);
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index e947572a521e..517988e60cfc 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -3,7 +3,7 @@
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index f4b719bde763..7996c04393d5 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -24,7 +24,8 @@
 #include <linux/slab.h>
 #include <linux/page-flags.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmapool.h>
 #include <linux/list.h>
 #include <linux/scatterlist.h>
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
deleted file mode 100644
index d785187a6f8a..000000000000
--- a/arch/arm/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASMARM_DMA_CONTIGUOUS_H
-#define ASMARM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index 7c3001a6a775..77fcb7ee5ec9 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -2,13 +2,44 @@
 #ifndef ASM_ARM_DMA_DIRECT_H
 #define ASM_ARM_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+#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)
+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;
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 86405cc81385..fe9ef6f79e9c 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -6,7 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <linux/kref.h>
 
 struct dma_iommu_mapping {
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index bdd80ddbca34..77082246a5e1 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -6,9 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-
-#include <asm/memory.h>
 
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
@@ -23,74 +20,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return NULL;
 }
 
-#ifdef __arch_page_to_dma
-#error Please update to __arch_pfn_to_dma
-#endif
-
-/*
- * dma_to_pfn/pfn_to_dma/dma_to_virt/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.
- */
-#ifndef __arch_pfn_to_dma
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
-	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)
-		pfn += dev->dma_pfn_offset;
-
-	return pfn;
-}
-
-static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
-{
-	if (dev) {
-		unsigned long pfn = dma_to_pfn(dev, addr);
-
-		return phys_to_virt(__pfn_to_phys(pfn));
-	}
-
-	return (void *)__bus_to_virt((unsigned long)addr);
-}
-
-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));
-}
-
-#else
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	return __arch_pfn_to_dma(dev, pfn);
-}
-
-static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
-{
-	return __arch_dma_to_pfn(dev, addr);
-}
-
-static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
-{
-	return __arch_dma_to_virt(dev, addr);
-}
-
-static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
-{
-	return __arch_virt_to_dma(dev, addr);
-}
-#endif
-
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index feb206bdf6e1..bb368938fc49 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -10,7 +10,7 @@
 #include <linux/clk-provider.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmaengine.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -884,6 +884,7 @@ early_param("rproc_mem", early_rproc_mem);
 
 void __init da8xx_rproc_reserve_cma(void)
 {
+	struct cma *cma;
 	int ret;
 
 	if (!rproc_base || !rproc_size) {
@@ -897,13 +898,16 @@ void __init da8xx_rproc_reserve_cma(void)
 	pr_info("%s: reserving 0x%lx @ 0x%lx...\n",
 		__func__, rproc_size, (unsigned long)rproc_base);
 
-	ret = dma_declare_contiguous(&da8xx_dsp.dev, rproc_size, rproc_base, 0);
-	if (ret)
-		pr_err("%s: dma_declare_contiguous failed %d\n", __func__, ret);
-	else
-		rproc_mem_inited = true;
+	ret = dma_contiguous_reserve_area(rproc_size, rproc_base, 0, &cma,
+			true);
+	if (ret) {
+		pr_err("%s: dma_contiguous_reserve_area failed %d\n",
+			__func__, ret);
+		return;
+	}
+	da8xx_dsp.dev.cma_area = cma;
+	rproc_mem_inited = true;
 }
-
 #else
 
 void __init da8xx_rproc_reserve_cma(void)
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 56bf29523c65..db607955a7e4 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -5,7 +5,7 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clocksource.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 3da4c0920198..a329e50928b6 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -16,7 +16,7 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/leds.h>
 #include <linux/platform_data/asoc-mx27vis.h>
 #include <sound/tlv320aic32x4.h>
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index 96845a4eaf57..7f780ad2d459 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 184262d660ba..000f672a94c9 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -29,6 +29,7 @@
 #include <linux/sched_clock.h>
 #include <linux/irqchip/irq-ixp4xx.h>
 #include <linux/platform_data/timer-ixp4xx.h>
+#include <linux/dma-map-ops.h>
 #include <mach/udc.h>
 #include <mach/hardware.h>
 #include <mach/io.h>
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index 638808c4e122..09a65c2dfd73 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -8,6 +8,7 @@
  */
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
@@ -24,8 +25,7 @@
 
 #include "keystone.h"
 
-static unsigned long keystone_dma_pfn_offset __read_mostly;
-
+#ifdef CONFIG_ARM_LPAE
 static int keystone_platform_notifier(struct notifier_block *nb,
 				      unsigned long event, void *data)
 {
@@ -38,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 		return NOTIFY_BAD;
 
 	if (!dev->of_node) {
-		dev->dma_pfn_offset = keystone_dma_pfn_offset;
-		dev_err(dev, "set dma_pfn_offset%08lx\n",
-			dev->dma_pfn_offset);
+		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
+						KEYSTONE_LOW_PHYS_START,
+						KEYSTONE_HIGH_PHYS_SIZE);
+		dev_err(dev, "set dma_offset%08llx%s\n",
+			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
+			ret ? " failed" : "");
 	}
 	return NOTIFY_OK;
 }
@@ -48,14 +51,14 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 static struct notifier_block platform_nb = {
 	.notifier_call = keystone_platform_notifier,
 };
+#endif /* CONFIG_ARM_LPAE */
 
 static void __init keystone_init(void)
 {
-	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
-		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
-						   KEYSTONE_LOW_PHYS_START);
+#ifdef CONFIG_ARM_LPAE
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
 		bus_register_notifier(&platform_bus_type, &platform_nb);
-	}
+#endif
 	keystone_pm_runtime_init();
 }
 
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 8f8748a0c84f..49e3c8d20c2f 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -25,7 +25,7 @@
 #include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/smp.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/mbus.h>
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index 1142560e0078..36bc0000cb6a 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -14,42 +14,11 @@
  * OMAP-1510 bus address is translated into a Local Bus address if the
  * OMAP bus type is lbus. We do the address translation based on the
  * device overriding the defaults used in the dma-mapping API.
- * Note that the is_lbus_device() test is not very efficient on 1510
- * because of the strncmp().
  */
-#if defined(CONFIG_ARCH_OMAP15XX) && !defined(__ASSEMBLER__)
 
 /*
  * OMAP-1510 Local Bus address offset
  */
 #define OMAP1510_LB_OFFSET	UL(0x30000000)
 
-#define virt_to_lbus(x)		((x) - PAGE_OFFSET + OMAP1510_LB_OFFSET)
-#define lbus_to_virt(x)		((x) - OMAP1510_LB_OFFSET + PAGE_OFFSET)
-#define is_lbus_device(dev)	(cpu_is_omap15xx() && dev && (strncmp(dev_name(dev), "ohci", 4) == 0))
-
-#define __arch_pfn_to_dma(dev, pfn)	\
-	({ dma_addr_t __dma = __pfn_to_phys(pfn); \
-	   if (is_lbus_device(dev)) \
-		__dma = __dma - PHYS_OFFSET + OMAP1510_LB_OFFSET; \
-	   __dma; })
-
-#define __arch_dma_to_pfn(dev, addr)	\
-	({ dma_addr_t __dma = addr;				\
-	   if (is_lbus_device(dev))				\
-		__dma += PHYS_OFFSET - OMAP1510_LB_OFFSET;	\
-	   __phys_to_pfn(__dma);				\
-	})
-
-#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
-						lbus_to_virt(addr) : \
-						__phys_to_virt(addr)); })
-
-#define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
-					   (dma_addr_t) (is_lbus_device(dev) ? \
-						virt_to_lbus(__addr) : \
-						__virt_to_phys(__addr)); })
-
-#endif	/* CONFIG_ARCH_OMAP15XX */
-
 #endif
diff --git a/arch/arm/mach-omap1/usb.c b/arch/arm/mach-omap1/usb.c
index d8e9bbda8f7b..ba8566204ea9 100644
--- a/arch/arm/mach-omap1/usb.c
+++ b/arch/arm/mach-omap1/usb.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
 #include <linux/io.h>
 
 #include <asm/irq.h>
@@ -542,6 +543,25 @@ static u32 __init omap1_usb2_init(unsigned nwires, unsigned alt_pingroup)
 /* ULPD_APLL_CTRL */
 #define APLL_NDPLL_SWITCH	(1 << 0)
 
+static int omap_1510_usb_ohci_notifier(struct notifier_block *nb,
+		unsigned long event, void *data)
+{
+	struct device *dev = data;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	if (strncmp(dev_name(dev), "ohci", 4) == 0 &&
+	    dma_direct_set_offset(dev, PHYS_OFFSET, OMAP1510_LB_OFFSET,
+			(u64)-1))
+		WARN_ONCE(1, "failed to set DMA offset\n");
+	return NOTIFY_OK;
+}
+
+static struct notifier_block omap_1510_usb_ohci_nb = {
+	.notifier_call		= omap_1510_usb_ohci_notifier,
+};
+
 static void __init omap_1510_usb_init(struct omap_usb_config *config)
 {
 	unsigned int val;
@@ -600,6 +620,8 @@ static void __init omap_1510_usb_init(struct omap_usb_config *config)
 	if (config->register_host) {
 		int status;
 
+		bus_register_notifier(&platform_bus_type,
+				      &omap_1510_usb_ohci_nb);
 		ohci_device.dev.platform_data = config;
 		status = platform_device_register(&ohci_device);
 		if (status)
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index c42ff8c314c8..e00f5b3b9293 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -9,7 +9,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 287ef898a55e..6bfd2b884505 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/cachetype.h>
@@ -176,6 +177,8 @@ static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist
 const struct dma_map_ops arm_nommu_dma_ops = {
 	.alloc			= arm_nommu_dma_alloc,
 	.free			= arm_nommu_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_nommu_dma_mmap,
 	.map_page		= arm_nommu_dma_map_page,
 	.unmap_page		= arm_nommu_dma_unmap_page,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8a8949174b1c..c4b8df2ad328 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -15,9 +15,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
@@ -35,7 +33,6 @@
 #include <asm/dma-iommu.h>
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
-#include <asm/dma-contiguous.h>
 #include <xen/swiotlb-xen.h>
 
 #include "dma.h"
@@ -199,6 +196,8 @@ static int arm_dma_supported(struct device *dev, u64 mask)
 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,
@@ -226,6 +225,8 @@ static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 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,
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 45f9d5ec2360..d57112a276f5 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -18,7 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sizes.h>
 #include <linux/stop_machine.h>
 #include <linux/swiotlb.h>
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index d3ef975a0965..467fa225c3d0 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/cpu.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 6c45350e33aa..93e87b287556 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -6,7 +6,7 @@
 
 #include <linux/gfp.h>
 #include <linux/cache.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-iommu.h>
 #include <xen/xen.h>
 #include <xen/swiotlb-xen.h>
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f0bf86d81622..a53c1e0fb017 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -21,8 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
@@ -429,6 +428,8 @@ void __init bootmem_init(void)
 	arm64_hugetlb_cma_reserve();
 #endif
 
+	dma_pernuma_cma_reserve();
+
 	/*
 	 * sparse_init() tries to allocate memory from memblock, so must be
 	 * done after the fixed reservations
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index a5909091cb14..03df07a831fc 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -15,7 +15,7 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index 0481f4e34538..e4cab16056d6 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -7,7 +7,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/start_kernel.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/screen_info.h>
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 8f6571ae27c8..c3a775a7e8f9 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -2,9 +2,7 @@
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
 #include <linux/cache.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index 25f388d9cfcc..00b9a81075dd 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -5,7 +5,7 @@
  * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved.
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 #include <linux/genalloc.h>
 #include <linux/module.h>
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 996c410f2152..f11a8ebfe5c2 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -8,6 +8,7 @@ menu "Processor type and features"
 
 config IA64
 	bool
+	select ARCH_HAS_DMA_MARK_CLEAN
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ACPI
@@ -32,8 +33,6 @@ config IA64
 	select TTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select DMA_NONCOHERENT_MMAP
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 656a4888c300..9148ddbf02e5 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -33,7 +33,7 @@
 #include <linux/bitops.h>         /* hweight64() */
 #include <linux/crash_dump.h>
 #include <linux/iommu-helper.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/prefetch.h>
 #include <linux/swiotlb.h>
 
@@ -485,8 +485,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	ASSERT(((unsigned long) ioc->res_hint & (sizeof(unsigned long) - 1UL)) == 0);
 	ASSERT(res_ptr < res_end);
 
-	boundary_size = (unsigned long long)dma_get_seg_boundary(dev) + 1;
-	boundary_size = ALIGN(boundary_size, 1ULL << iovp_shift) >> iovp_shift;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, iovp_shift);
 
 	BUG_ON(ioc->ibase & ~iovp_mask);
 	shift = ioc->ibase >> iovp_shift;
@@ -2071,6 +2070,8 @@ static const struct dma_map_ops sba_dma_ops = {
 	.dma_supported		= sba_dma_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 
 static int __init
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 09ef9ce9988d..cd0c166bfbc2 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
@@ -7,15 +7,3 @@ int iommu_detected __read_mostly;
 
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
-
-void *arch_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
-{
-	dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-}
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 8e7b8c6c576e..d8686bf3ae2f 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -8,7 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmar.h>
 #include <linux/efi.h>
 #include <linux/elf.h>
@@ -73,8 +73,7 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index b1ca3522eccc..1c1b875fadc1 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -6,7 +6,7 @@
 
 #undef DEBUG
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index d7bebd04247b..04d091ade417 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -8,9 +8,8 @@
  */
 
 #include <linux/device.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
-#include <linux/dma-debug.h>
 #include <linux/export.h>
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c
index e09b66e43cb6..81dffe43b18c 100644
--- a/arch/microblaze/mm/consistent.c
+++ b/arch/microblaze/mm/consistent.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/init.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cpuinfo.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 0902c459c385..45da639bd22c 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -7,7 +7,7 @@
  * for more details.
  */
 
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 440614dc9de2..c695d103bf6d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1136,7 +1136,6 @@ config DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_DMA_SET_UNCACHED
 	select DMA_NONCOHERENT_MMAP
-	select DMA_NONCOHERENT_CACHE_SYNC
 	select NEED_DMA_MAP_STATE
 
 config SYS_HAS_EARLY_PRINTK
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index df56bf4179e3..49061b870680 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
@@ -52,7 +52,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index ad1aecc4b401..df70308db0e6 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -168,7 +168,7 @@ void __init octeon_pci_dma_init(void)
 }
 #endif /* CONFIG_PCI */
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
@@ -177,7 +177,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index 14e352651ce9..9a640118316c 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef _MIPS_DMA_DIRECT_H
 #define _MIPS_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 daddr);
+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 daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/include/asm/jazzdma.h b/arch/mips/include/asm/jazzdma.h
index d13f940022d5..c831da7fa898 100644
--- a/arch/mips/include/asm/jazzdma.h
+++ b/arch/mips/include/asm/jazzdma.h
@@ -10,8 +10,6 @@
  */
 extern unsigned long vdma_alloc(unsigned long paddr, unsigned long size);
 extern int vdma_free(unsigned long laddr);
-extern int vdma_remap(unsigned long laddr, unsigned long paddr,
-		      unsigned long size);
 extern unsigned long vdma_phys2log(unsigned long paddr);
 extern unsigned long vdma_log2phys(unsigned long laddr);
 extern void vdma_stats(void);		/* for debugging only */
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 014773f0bfcd..461457b28982 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,8 +16,7 @@
 #include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
@@ -209,76 +208,6 @@ int vdma_free(unsigned long laddr)
 
 EXPORT_SYMBOL(vdma_free);
 
-/*
- * Map certain page(s) to another physical address.
- * Caller must have allocated the page(s) before.
- */
-int vdma_remap(unsigned long laddr, unsigned long paddr, unsigned long size)
-{
-	int first, pages;
-
-	if (laddr > 0xffffff) {
-		if (vdma_debug)
-			printk
-			    ("vdma_map: Invalid logical address: %08lx\n",
-			     laddr);
-		return -EINVAL; /* invalid logical address */
-	}
-	if (paddr > 0x1fffffff) {
-		if (vdma_debug)
-			printk
-			    ("vdma_map: Invalid physical address: %08lx\n",
-			     paddr);
-		return -EINVAL; /* invalid physical address */
-	}
-
-	pages = (((paddr & (VDMA_PAGESIZE - 1)) + size) >> 12) + 1;
-	first = laddr >> 12;
-	if (vdma_debug)
-		printk("vdma_remap: first=%x, pages=%x\n", first, pages);
-	if (first + pages > VDMA_PGTBL_ENTRIES) {
-		if (vdma_debug)
-			printk("vdma_alloc: Invalid size: %08lx\n", size);
-		return -EINVAL;
-	}
-
-	paddr &= ~(VDMA_PAGESIZE - 1);
-	while (pages > 0 && first < VDMA_PGTBL_ENTRIES) {
-		if (pgtbl[first].owner != laddr) {
-			if (vdma_debug)
-				printk("Trying to remap other's pages.\n");
-			return -EPERM;	/* not owner */
-		}
-		pgtbl[first].frame = paddr;
-		paddr += VDMA_PAGESIZE;
-		first++;
-		pages--;
-	}
-
-	/*
-	 * Update translation table
-	 */
-	r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
-
-	if (vdma_debug > 2) {
-		int i;
-		pages = (((paddr & (VDMA_PAGESIZE - 1)) + size) >> 12) + 1;
-		first = laddr >> 12;
-		printk("LADDR: ");
-		for (i = first; i < first + pages; i++)
-			printk("%08x ", i << 12);
-		printk("\nPADDR: ");
-		for (i = first; i < first + pages; i++)
-			printk("%08x ", pgtbl[i].frame);
-		printk("\nOWNER: ");
-		for (i = first; i < first + pages; i++)
-			printk("%08x ", pgtbl[i].owner);
-		printk("\n");
-	}
-
-	return 0;
-}
-
 /*
  * Translate a physical address to a logical address.
  * This will return the logical address of the first
@@ -562,26 +491,34 @@ int vdma_get_enable(int channel)
 static void *jazz_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
+	struct page *page;
 	void *ret;
 
-	ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-	if (!ret)
-		return NULL;
+	if (attrs & DMA_ATTR_NO_WARN)
+		gfp |= __GFP_NOWARN;
 
+	size = PAGE_ALIGN(size);
+	page = alloc_pages(gfp, get_order(size));
+	if (!page)
+		return NULL;
+	ret = page_address(page);
+	memset(ret, 0, size);
 	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
-	if (*dma_handle == DMA_MAPPING_ERROR) {
-		dma_direct_free_pages(dev, size, ret, *dma_handle, attrs);
-		return NULL;
-	}
+	if (*dma_handle == DMA_MAPPING_ERROR)
+		goto out_free_pages;
+	arch_dma_prep_coherent(page, size);
+	return (void *)(UNCAC_BASE + __pa(ret));
 
-	return ret;
+out_free_pages:
+	__free_pages(page, get_order(size));
+	return NULL;
 }
 
 static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	vdma_free(dma_handle);
-	dma_direct_free_pages(dev, size, vaddr, dma_handle, attrs);
+	__free_pages(virt_to_page(vaddr), get_order(size));
 }
 
 static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
@@ -678,9 +615,9 @@ const struct dma_map_ops jazz_dma_ops = {
 	.sync_single_for_device	= jazz_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
-	.dma_supported		= dma_direct_supported,
-	.cache_sync		= arch_dma_cache_sync,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(jazz_dma_ops);
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 335bd188b8b4..ee8636ccded2 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -24,7 +24,7 @@
 #include <linux/kexec.h>
 #include <linux/sizes.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/decompress/generic.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
diff --git a/arch/mips/loongson2ef/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index e122292bf666..cea167d8aba8 100644
--- a/arch/mips/loongson2ef/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & 0x7fffffff;
 }
diff --git a/arch/mips/loongson2ef/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index abf0e39d7e46..3c9e99456357 100644
--- a/arch/mips/loongson2ef/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	if (dma_addr > 0x8fffffff)
 		return dma_addr;
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index dbfe6e82fddd..364f2f27c872 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -4,7 +4,7 @@
 #include <linux/swiotlb.h>
 #include <boot_param.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
@@ -13,7 +13,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 563c2c0d0c81..38d3d9143b47 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -5,8 +5,7 @@
  * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
  */
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
@@ -55,22 +54,34 @@ void *arch_dma_set_uncached(void *addr, size_t size)
 	return (void *)(__pa(addr) + UNCAC_BASE);
 }
 
-static inline void dma_sync_virt(void *addr, size_t size,
+static inline void dma_sync_virt_for_device(void *addr, size_t size,
 		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		dma_cache_wback((unsigned long)addr, size);
 		break;
-
 	case DMA_FROM_DEVICE:
 		dma_cache_inv((unsigned long)addr, size);
 		break;
-
 	case DMA_BIDIRECTIONAL:
 		dma_cache_wback_inv((unsigned long)addr, size);
 		break;
+	default:
+		BUG();
+	}
+}
 
+static inline void dma_sync_virt_for_cpu(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
 	default:
 		BUG();
 	}
@@ -82,7 +93,7 @@ static inline void dma_sync_virt(void *addr, size_t size,
  * configured then the bulk of this loop gets optimized out.
  */
 static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+		enum dma_data_direction dir, bool for_device)
 {
 	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
 	unsigned long offset = paddr & ~PAGE_MASK;
@@ -90,18 +101,20 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 
 	do {
 		size_t len = left;
+		void *addr;
 
 		if (PageHighMem(page)) {
-			void *addr;
-
 			if (offset + len > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
+		}
+
+		addr = kmap_atomic(page);
+		if (for_device)
+			dma_sync_virt_for_device(addr + offset, len, dir);
+		else
+			dma_sync_virt_for_cpu(addr + offset, len, dir);
+		kunmap_atomic(addr);
 
-			addr = kmap_atomic(page);
-			dma_sync_virt(addr + offset, len, dir);
-			kunmap_atomic(addr);
-		} else
-			dma_sync_virt(page_address(page) + offset, size, dir);
 		offset = 0;
 		page++;
 		left -= len;
@@ -111,7 +124,7 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	dma_sync_phys(paddr, size, dir);
+	dma_sync_phys(paddr, size, dir, true);
 }
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
@@ -119,18 +132,10 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
 	if (cpu_needs_post_dma_flush())
-		dma_sync_phys(paddr, size, dir);
+		dma_sync_phys(paddr, size, dir, false);
 }
 #endif
 
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	dma_sync_virt(vaddr, size, direction);
-}
-
 #ifdef CONFIG_DMA_PERDEV_COHERENT
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent)
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index 490953f51528..cef4a47ab063 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -170,12 +170,12 @@ static inline dma_addr_t ar2315_dev_offset(struct device *dev)
 	return 0;
 }
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + ar2315_dev_offset(dev);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr - ar2315_dev_offset(dev);
 }
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 9b3cc775c55e..50f7d42cca5a 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -25,7 +25,7 @@
 /*
  * Common phys<->dma mapping for platforms using pci xtalk bridge
  */
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
@@ -33,7 +33,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return bc->baddr + paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & ~(0xffUL << 56);
 }
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
index fa7b17cb5385..20c6da9d76bc 100644
--- a/arch/mips/sgi-ip32/ip32-dma.c
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -18,7 +18,7 @@
 
 #define RAM_OFFSET_MASK 0x3fffffffUL
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
 
@@ -27,7 +27,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dma_addr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
 
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index 69d762182d49..2ac8e6c82a61 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -3,7 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/cache.h>
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 345727638d52..1b16d97e7da7 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -13,7 +13,7 @@
  * DMA mapping callbacks...
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index cd4afe1e7a6c..d9a50f7a666c 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -195,7 +195,6 @@ config PA11
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH
 	def_bool y
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index a5f3e50fe976..80fa0650736b 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -30,6 +30,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/export.h>
+#include <linux/dma-map-ops.h>
 #include <asm/hardware.h>
 #include <asm/io.h>
 #include <asm/pdc.h>
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 38c68e131bbe..36610a5c029f 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -26,7 +26,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma.h>    /* for DMA_CHUNK_SIZE */
@@ -454,9 +454,3 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
-
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	flush_kernel_dcache_range((unsigned long)vaddr, size);
-}
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index abc154d784b0..128304cbee1d 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -2,12 +2,12 @@
 #ifndef ASM_POWERPC_DMA_DIRECT_H
 #define ASM_POWERPC_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + dev->archdata.dma_offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	return daddr - dev->archdata.dma_offset;
 }
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 5032f1593299..deef7c94d7b6 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -12,7 +12,7 @@
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/bitops.h>
 #include <asm/machdep.h>
 #include <asm/types.h>
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 63ed7e3b0ba3..6436f0b41539 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -9,7 +9,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 9053fc9d20c7..a1c744194018 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -138,4 +138,6 @@ const struct dma_map_ops dma_iommu_ops = {
 	.get_required_mask	= dma_iommu_get_required_mask,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9704f3f76e63..5b69a6a72a0e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -172,7 +172,6 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	int largealloc = npages > 15;
 	int pass = 0;
 	unsigned long align_mask;
-	unsigned long boundary_size;
 	unsigned long flags;
 	unsigned int pool_nr;
 	struct iommu_pool *pool;
@@ -236,15 +235,9 @@ static unsigned long iommu_range_alloc(struct device *dev,
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << tbl->it_page_shift);
-	else
-		boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
-	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
-
 	n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
-			     boundary_size >> tbl->it_page_shift, align_mask);
+			dma_get_seg_boundary_nr_pages(dev, tbl->it_page_shift),
+			align_mask);
 	if (n == -1) {
 		if (likely(pass == 0)) {
 			/* First try the pool from the start */
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 5ab4f868e919..30260b5d146d 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/tlbflush.h>
 #include <asm/dma.h>
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 3542b7bd6a46..c62aaa29a9d5 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/export.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
@@ -696,6 +696,8 @@ static const struct dma_map_ops ps3_sb_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
 
 static const struct dma_map_ops ps3_ioc0_dma_ops = {
@@ -708,6 +710,8 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
 
 /**
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index a6f101c958e8..8c6e509f6967 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -40,7 +40,7 @@
 #include <linux/export.h>
 #include <linux/console.h>
 #include <linux/kobject.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 0487b26f6f1a..b2797cfe4e2b 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -20,7 +20,7 @@
 #include <linux/console.h>
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/kobject.h>
 
 #include <asm/iommu.h>
@@ -608,6 +608,8 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.get_required_mask = dma_iommu_get_required_mask,
 	.mmap		   = dma_common_mmap,
 	.get_sgtable	   = dma_common_get_sgtable,
+	.alloc_pages	   = dma_common_alloc_pages,
+	.free_pages	   = dma_common_free_pages,
 };
 
 /**
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d44e522c569b..c64a95ae830f 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -37,7 +37,7 @@
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/kernel_stat.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/pfn.h>
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 64b1399a73f0..ebc9a49523aa 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/iommu-helper.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/vmalloc.h>
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
@@ -261,13 +261,11 @@ static unsigned long __dma_alloc_iommu(struct device *dev,
 				       unsigned long start, int size)
 {
 	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
-	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, zdev->start_dma >> PAGE_SHIFT,
-				boundary_size, 0);
+				dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT),
+				0);
 }
 
 static dma_addr_t dma_alloc_address(struct device *dev, int size)
@@ -670,6 +668,8 @@ const struct dma_map_ops s390_pci_dma_ops = {
 	.unmap_page	= s390_dma_unmap_pages,
 	.mmap		= dma_common_mmap,
 	.get_sgtable	= dma_common_get_sgtable,
+	.alloc_pages	= dma_common_alloc_pages,
+	.free_pages	= dma_common_free_pages,
 	/* dma_supported is unconditionally true without a callback */
 };
 EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 665cad452798..bac8a058ebd7 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -13,6 +13,7 @@
 
 #include <cpu/sh7723.h>
 
+#include <linux/dma-map-ops.h>
 #include <linux/clkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index dd427bac5cde..bab91a99124e 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -36,6 +36,7 @@
 #include <linux/usb/r8a66597.h>
 #include <linux/usb/renesas_usbhs.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <media/drv-intf/renesas-ceu.h>
 #include <media/i2c/mt9t112.h>
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 96538ba3aa32..eeb5ce341efd 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -14,7 +14,6 @@
 
 #include <linux/clkdev.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
 #include <linux/i2c.h>
@@ -33,6 +32,7 @@
 #include <linux/sh_intc.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <mach/kfr2r09.h>
 
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 9ed369dad62d..6703a2122c0d 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -5,7 +5,7 @@
  * Copyright (C) 2008 Magnus Damm
  */
 #include <linux/clkdev.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index 32f5dd944889..8d6541ba0186 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -32,6 +32,7 @@
 #include <linux/smc91x.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <mach-se/mach/se7724.h>
 #include <media/drv-intf/renesas-ceu.h>
diff --git a/arch/sh/drivers/pci/fixups-dreamcast.c b/arch/sh/drivers/pci/fixups-dreamcast.c
index 7be8694c0d13..41e4daee8f04 100644
--- a/arch/sh/drivers/pci/fixups-dreamcast.c
+++ b/arch/sh/drivers/pci/fixups-dreamcast.c
@@ -19,7 +19,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index 6ab0b7377f66..a3903304f33f 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -13,7 +13,6 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/types.h>
-#include <linux/dma-debug.h>
 #include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index e0b568aaa701..4468289ab2ca 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/async.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
@@ -31,6 +32,8 @@ struct sh7786_pcie_port {
 static struct sh7786_pcie_port *sh7786_pcie_ports;
 static unsigned int nr_ports;
 static unsigned long dma_pfn_offset;
+size_t memsize;
+u64 memstart;
 
 static struct sh7786_pcie_hwops {
 	int (*core_init)(void);
@@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	struct pci_channel *chan = port->hose;
 	unsigned int data;
 	phys_addr_t memstart, memend;
-	size_t memsize;
 	int ret, i, win;
 
 	/* Begin initialization */
@@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	memstart = ALIGN_DOWN(memstart, memsize);
 	memsize = roundup_pow_of_two(memend - memstart);
 
-	dma_pfn_offset = memstart >> PAGE_SHIFT;
-
 	/*
 	 * If there's more than 512MB of memory, we need to roll over to
 	 * LAR1/LAMR1.
@@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
 
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	pdev->dev.dma_pfn_offset = dma_pfn_offset;
+	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
+			      __pa(memory_start) - memstart, memsize);
 }
 
 static int __init sh7786_pcie_core_init(void)
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index cd46a9825e3c..6a44c0e7ba40 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -3,7 +3,7 @@
  * Copyright (C) 2004 - 2007  Paul Mundt
  */
 #include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
diff --git a/arch/sparc/kernel/iommu-common.c b/arch/sparc/kernel/iommu-common.c
index 59cb16691322..23ca75f09277 100644
--- a/arch/sparc/kernel/iommu-common.c
+++ b/arch/sparc/kernel/iommu-common.c
@@ -166,13 +166,6 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << iommu->table_shift);
-	else
-		boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
-
-	boundary_size = boundary_size >> iommu->table_shift;
 	/*
 	 * if the skip_span_boundary_check had been set during init, we set
 	 * things up so that iommu_is_span_boundary() merely checks if the
@@ -181,6 +174,9 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
 		shift = 0;
 		boundary_size = iommu->poolsize * iommu->nr_pools;
+	} else {
+		boundary_size = dma_get_seg_boundary_nr_pages(dev,
+					iommu->table_shift);
 	}
 	n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
 			     boundary_size, align_mask);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4ae7388b1bff..a034f571d869 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/errno.h>
 #include <linux/iommu-helper.h>
 #include <linux/bitmap.h>
@@ -472,8 +472,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	outs->dma_length = 0;
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index d6874c9b639f..8e1d72a16759 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -38,7 +38,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of_device.h>
 
 #include <asm/io.h>
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 14b93c5564e3..9de57e88f7a1 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/log2.h>
 #include <linux/of_device.h>
+#include <linux/dma-map-ops.h>
 #include <asm/iommu-common.h>
 
 #include <asm/iommu.h>
@@ -508,8 +509,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	iommu_batch_start(dev, prot, ~0UL);
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index 430a47a1b6ae..bf3e6d2fe5d9 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -11,7 +11,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/bitops.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 3a388b1c5d4b..0c0342e5b10d 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index fed67eafcacc..bb1654fe0ce7 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -8,10 +8,8 @@
  */
 
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
-#include <linux/dma-contiguous.h>
 
 extern int iommu_merge;
 extern int panic_on_overflow;
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e89031e9c847..9ac696487b13 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/atomic.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <asm/mtrr.h>
 #include <asm/proto.h>
 #include <asm/iommu.h>
@@ -96,8 +97,7 @@ static unsigned long alloc_iommu(struct device *dev, int size,
 
 	base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
 			   PAGE_SIZE) >> PAGE_SHIFT;
-	boundary_size = ALIGN((u64)dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
@@ -468,7 +468,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 {
 	void *vaddr;
 
-	vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs);
+	vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
 	if (!vaddr ||
 	    !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24))
 		return vaddr;
@@ -480,7 +480,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		goto out_free;
 	return vaddr;
 out_free:
-	dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, *dma_addr, attrs);
 	return NULL;
 }
 
@@ -490,7 +490,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 		   dma_addr_t dma_addr, unsigned long attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
-	dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, dma_addr, attrs);
 }
 
 static int no_agp;
@@ -678,6 +678,8 @@ static const struct dma_map_ops gart_dma_ops = {
 	.get_sgtable			= dma_common_get_sgtable,
 	.dma_supported			= dma_direct_supported,
 	.get_required_mask		= dma_direct_get_required_mask,
+	.alloc_pages			= dma_direct_alloc_pages,
+	.free_pages			= dma_direct_free_pages,
 };
 
 static void gart_iommu_shutdown(void)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 5dcedad21dff..de234e7a8962 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-debug.h>
 #include <linux/iommu.h>
 #include <linux/dmar.h>
 #include <linux/export.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b16caee53bea..84f581c91db4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,6 +7,7 @@
  */
 #include <linux/console.h>
 #include <linux/crash_dump.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/init_ohci1394_dma.h>
@@ -20,6 +21,7 @@
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
 #include <linux/static_call.h>
+#include <linux/swiotlb.h>
 
 #include <uapi/linux/mount.h>
 
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 11c0e80b9ed4..5701d5ba3df4 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -132,7 +132,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
 	struct device *dev = &pdev->dev;
 	u32 amba_base, max_amba_addr;
-	int i;
+	int i, ret;
 
 	if (!instance)
 		return;
@@ -140,7 +140,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
 	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
 
-	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
+	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
+	if (ret)
+		dev_err(dev, "sta2x11: could not set DMA offset\n");
 
 	dev->bus_dma_limit = max_amba_addr;
 	pci_set_consistent_dma_mask(pdev, max_amba_addr);
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 33293ce01d8d..19ae3e4fe4e9 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -2,7 +2,7 @@
 
 /* Glue code to lib/swiotlb-xen.c */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pci.h>
 #include <xen/swiotlb-xen.h>
 
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 17c4384f8495..94955caa4488 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -11,8 +11,7 @@
  * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
  */
 
-#include <linux/dma-contiguous.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index ad9d59d93f39..c6fc83efee0c 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -26,7 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/mm.h>
 #include <linux/of_fdt.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/bootparam.h>
 #include <asm/page.h>
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 6f89c16f45f3..9929ff50c0c0 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/dma-map-ops.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
@@ -1178,8 +1179,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	*dma_addr = dmaaddr;
 	*dma_size = size;
 
-	dev->dma_pfn_offset = PFN_DOWN(offset);
-	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
+	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
+
+	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 684c726828e1..a896e5e87c93 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -13,7 +13,7 @@
 #include <linux/kthread.h>
 #include <linux/dmi.h>
 #include <linux/nls.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pgtable.h>
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 3b9404921da9..b919e6d01d9a 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1798,6 +1798,8 @@ static void device_release(struct kobject *kobj)
 	 */
 	devres_release_all(dev);
 
+	kfree(dev->dma_range_map);
+
 	if (dev->release)
 		dev->release(dev);
 	else if (dev->type && dev->type->release)
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b52d69eb4e71..b42229b74fd6 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -19,7 +19,7 @@
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 626cf7fd033a..e55384dc115b 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -10,7 +10,7 @@
 #include <linux/device.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-heap.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/highmem.h>
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 020cb15a4d8f..9811c40956e5 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -674,17 +674,16 @@ static void ar_context_link_page(struct ar_context *ctx, unsigned int index)
 
 static void ar_context_release(struct ar_context *ctx)
 {
+	struct device *dev = ctx->ohci->card.device;
 	unsigned int i;
 
 	vunmap(ctx->buffer);
 
-	for (i = 0; i < AR_BUFFERS; i++)
-		if (ctx->pages[i]) {
-			dma_unmap_page(ctx->ohci->card.device,
-				       ar_buffer_bus(ctx, i),
-				       PAGE_SIZE, DMA_FROM_DEVICE);
-			__free_page(ctx->pages[i]);
-		}
+	for (i = 0; i < AR_BUFFERS; i++) {
+		if (ctx->pages[i])
+			dma_free_pages(dev, PAGE_SIZE, ctx->pages[i],
+				       ar_buffer_bus(ctx, i), DMA_FROM_DEVICE);
+	}
 }
 
 static void ar_context_abort(struct ar_context *ctx, const char *error_msg)
@@ -970,6 +969,7 @@ static void ar_context_tasklet(unsigned long data)
 static int ar_context_init(struct ar_context *ctx, struct fw_ohci *ohci,
 			   unsigned int descriptors_offset, u32 regs)
 {
+	struct device *dev = ohci->card.device;
 	unsigned int i;
 	dma_addr_t dma_addr;
 	struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES];
@@ -980,17 +980,13 @@ static int ar_context_init(struct ar_context *ctx, struct fw_ohci *ohci,
 	tasklet_init(&ctx->tasklet, ar_context_tasklet, (unsigned long)ctx);
 
 	for (i = 0; i < AR_BUFFERS; i++) {
-		ctx->pages[i] = alloc_page(GFP_KERNEL | GFP_DMA32);
+		ctx->pages[i] = dma_alloc_pages(dev, PAGE_SIZE, &dma_addr,
+						DMA_FROM_DEVICE, GFP_KERNEL);
 		if (!ctx->pages[i])
 			goto out_of_memory;
-		dma_addr = dma_map_page(ohci->card.device, ctx->pages[i],
-					0, PAGE_SIZE, DMA_FROM_DEVICE);
-		if (dma_mapping_error(ohci->card.device, dma_addr)) {
-			__free_page(ctx->pages[i]);
-			ctx->pages[i] = NULL;
-			goto out_of_memory;
-		}
 		set_page_private(ctx->pages[i], dma_addr);
+		dma_sync_single_for_device(dev, dma_addr, PAGE_SIZE,
+					   DMA_FROM_DEVICE);
 	}
 
 	for (i = 0; i < AR_BUFFERS; i++)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 5887f7f52f96..0644936afee2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -5,7 +5,7 @@
 // Author: Andrzej Hajda <a.hajda@samsung.com>
 
 #include <linux/dma-iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 1716a023bca0..7777f19c9d38 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -42,8 +42,6 @@ static int exynos_drm_alloc_buf(struct exynos_drm_gem *exynos_gem, bool kvmap)
 	if (exynos_gem->flags & EXYNOS_BO_WC ||
 			!(exynos_gem->flags & EXYNOS_BO_CACHABLE))
 		attr |= DMA_ATTR_WRITE_COMBINE;
-	else
-		attr |= DMA_ATTR_NON_CONSISTENT;
 
 	/* FBDev emulation requires kernel mapping */
 	if (!kvmap)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index ec602113be78..04be4cfcccc1 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -4,6 +4,7 @@
  * Author: Rob Clark <robdclark@gmail.com>
  */
 
+#include <linux/dma-map-ops.h>
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
 #include <linux/dma-buf.h>
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
index 985f2990ab0d..13d4d7ac0697 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
@@ -594,8 +594,7 @@ gk20a_instmem_new(struct nvkm_device *device, int index,
 
 		nvkm_info(&imem->base.subdev, "using IOMMU\n");
 	} else {
-		imem->attrs = DMA_ATTR_NON_CONSISTENT |
-			      DMA_ATTR_WEAK_ORDERING |
+		imem->attrs = DMA_ATTR_WEAK_ORDERING |
 			      DMA_ATTR_WRITE_COMBINE;
 
 		nvkm_info(&imem->base.subdev, "using DMA API\n");
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 2f26f85ef538..77497b45f9a2 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
@@ -810,8 +811,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 		 * because of an old DT, we need to set the DMA offset by hand
 		 * on our device since the RAM mapping is at 0 for the DMA bus,
 		 * unlike the CPU.
+		 *
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
 		 */
-		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 	}
 
 	backend->engine.node = dev->of_node;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 4b1b02c80f55..b9cf59443843 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/iommu-helper.h>
@@ -28,7 +28,6 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
-#include <linux/dma-contiguous.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
 #include <linux/iova.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index cd6e3c70ebb3..0cbcd3fc3e7e 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -10,9 +10,8 @@
 
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-iommu.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
@@ -572,6 +571,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
  * @size: Size of buffer in bytes
  * @dma_handle: Out argument for allocated DMA handle
  * @gfp: Allocation flags
+ * @prot: pgprot_t to use for the remapped mapping
  * @attrs: DMA attributes for this allocation
  *
  * If @size is less than PAGE_SIZE, then a full CPU page will be allocated,
@@ -580,14 +580,14 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
  * Return: Mapped virtual address, or NULL on failure.
  */
 static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+		dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot,
+		unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	bool coherent = dev_is_dma_coherent(dev);
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
-	pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
 	struct sg_table sgt;
@@ -1030,8 +1030,10 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	gfp |= __GFP_ZERO;
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && gfpflags_allow_blocking(gfp) &&
-	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS))
-		return iommu_dma_alloc_remap(dev, size, handle, gfp, attrs);
+	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) {
+		return iommu_dma_alloc_remap(dev, size, handle, gfp,
+				dma_pgprot(dev, PAGE_KERNEL, attrs), attrs);
+	}
 
 	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    !gfpflags_allow_blocking(gfp) && !coherent)
@@ -1052,6 +1054,34 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	return cpu_addr;
 }
 
+#ifdef CONFIG_DMA_REMAP
+static void *iommu_dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	if (!gfpflags_allow_blocking(gfp)) {
+		struct page *page;
+
+		page = dma_common_alloc_pages(dev, size, handle, dir, gfp);
+		if (!page)
+			return NULL;
+		return page_address(page);
+	}
+
+	return iommu_dma_alloc_remap(dev, size, handle, gfp | __GFP_ZERO,
+				     PAGE_KERNEL, 0);
+}
+
+static void iommu_dma_free_noncoherent(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t handle, enum dma_data_direction dir)
+{
+	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_free(dev, size, cpu_addr);
+}
+#else
+#define iommu_dma_alloc_noncoherent		NULL
+#define iommu_dma_free_noncoherent		NULL
+#endif /* CONFIG_DMA_REMAP */
+
 static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
@@ -1120,6 +1150,10 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
+	.alloc_noncoherent	= iommu_dma_alloc_noncoherent,
+	.free_noncoherent	= iommu_dma_free_noncoherent,
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 2e2ba294bb15..8651f6d4dfa0 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
@@ -37,7 +37,7 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
@@ -3747,6 +3747,8 @@ static const struct dma_map_ops intel_dma_ops = {
 	.dma_supported = dma_direct_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 	.get_required_mask = intel_get_required_mask,
 };
 
@@ -3814,7 +3816,7 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	 */
 	if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
 		tlb_addr = swiotlb_tbl_map_single(dev,
-				__phys_to_dma(dev, io_tlb_start),
+				phys_to_dma_unencrypted(dev, io_tlb_start),
 				paddr, size, aligned_size, dir, attrs);
 		if (tlb_addr == DMA_MAPPING_ERROR) {
 			goto swiotlb_error;
@@ -4000,6 +4002,8 @@ static const struct dma_map_ops bounce_dma_ops = {
 	.sync_sg_for_device	= bounce_sync_sg_for_device,
 	.map_resource		= bounce_map_resource,
 	.unmap_resource		= bounce_unmap_resource,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 	.dma_supported		= dma_direct_supported,
 };
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 534810b6be77..a7a9bc08dcd1 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -728,11 +728,6 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
-	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
-		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
-		return NULL;
-	}
-
 	data = kmalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return NULL;
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index 019bb47df915..32ab01e89196 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
-#include <linux/dma-contiguous.h>
 #include <linux/errno.h>
 #include <linux/firmware.h>
 #include <linux/interrupt.h>
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index d226ecadff8e..eb15c8c725ca 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else {
+		/*
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
+		 */
 #ifdef PHYS_PFN_OFFSET
-		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 #endif
 	}
 
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
index 28e89340fed9..e69e14379fc6 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
@@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	sdev->dev = &pdev->dev;
-	/* The DMA bus has the memory mapped at 0 */
-	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
+	/*
+	 * The DMA bus has the memory mapped at 0.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
+	 */
+	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
+	if (ret)
+		return ret;
 
 	ret = sun6i_csi_resource_request(sdev, pdev);
 	if (ret)
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index b9bb086785db..8a7c2c5711d5 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -35,6 +35,7 @@ config SCIF_BUS
 
 config VOP_BUS
 	tristate "VOP Bus Driver"
+	depends on HAS_DMA
 	select DMA_OPS
 	help
 	  This option is selected by any driver which registers a
diff --git a/drivers/misc/mic/bus/mic_bus.c b/drivers/misc/mic/bus/mic_bus.c
index ed9a8351c3bf..a08cb29692a8 100644
--- a/drivers/misc/mic/bus/mic_bus.c
+++ b/drivers/misc/mic/bus/mic_bus.c
@@ -9,6 +9,7 @@
  * This implementation is very similar to the the virtio bus driver
  * implementation @ drivers/virtio/virtio.c
  */
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
diff --git a/drivers/misc/mic/bus/scif_bus.c b/drivers/misc/mic/bus/scif_bus.c
index ae84109649d0..ad7c3604f151 100644
--- a/drivers/misc/mic/bus/scif_bus.c
+++ b/drivers/misc/mic/bus/scif_bus.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include "scif_bus.h"
 
diff --git a/drivers/misc/mic/bus/scif_bus.h b/drivers/misc/mic/bus/scif_bus.h
index 642cd43bcabc..4981eb56f879 100644
--- a/drivers/misc/mic/bus/scif_bus.h
+++ b/drivers/misc/mic/bus/scif_bus.h
@@ -12,7 +12,7 @@
  * Everything a scif driver needs to work with any particular scif
  * hardware abstraction layer.
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include <linux/mic_common.h>
 #include "../common/mic_dev.h"
diff --git a/drivers/misc/mic/bus/vop_bus.c b/drivers/misc/mic/bus/vop_bus.c
index 3c865534868a..6935ddca1bd5 100644
--- a/drivers/misc/mic/bus/vop_bus.c
+++ b/drivers/misc/mic/bus/vop_bus.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include "vop_bus.h"
 
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
index fb5b3989753d..8cb85b8b3e19 100644
--- a/drivers/misc/mic/host/mic_boot.c
+++ b/drivers/misc/mic/host/mic_boot.c
@@ -10,6 +10,7 @@
 #include <linux/firmware.h>
 #include <linux/pci.h>
 #include <linux/kmod.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mic_common.h>
 #include <linux/mic_bus.h>
 #include "../bus/scif_bus.h"
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 75dbd221dc59..19e195420e24 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1131,10 +1131,9 @@ static int au1000_probe(struct platform_device *pdev)
 	/* Allocate the data buffers
 	 * Snooping works fine with eth on all au1xxx
 	 */
-	aup->vaddr = (u32)dma_alloc_attrs(&pdev->dev, MAX_BUF_SIZE *
+	aup->vaddr = (u32)dma_alloc_coherent(&pdev->dev, MAX_BUF_SIZE *
 					  (NUM_TX_BUFFS + NUM_RX_BUFFS),
-					  &aup->dma_addr, 0,
-					  DMA_ATTR_NON_CONSISTENT);
+					  &aup->dma_addr, 0);
 	if (!aup->vaddr) {
 		dev_err(&pdev->dev, "failed to allocate data buffers\n");
 		err = -ENOMEM;
@@ -1310,9 +1309,8 @@ static int au1000_probe(struct platform_device *pdev)
 err_remap2:
 	iounmap(aup->mac);
 err_remap1:
-	dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
-			(void *)aup->vaddr, aup->dma_addr,
-			DMA_ATTR_NON_CONSISTENT);
+	dma_free_coherent(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
+			(void *)aup->vaddr, aup->dma_addr);
 err_vaddr:
 	free_netdev(dev);
 err_alloc:
@@ -1344,9 +1342,8 @@ static int au1000_remove(struct platform_device *pdev)
 		if (aup->tx_db_inuse[i])
 			au1000_ReleaseDB(aup, aup->tx_db_inuse[i]);
 
-	dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
-			(void *)aup->vaddr, aup->dma_addr,
-			DMA_ATTR_NON_CONSISTENT);
+	dma_free_coherent(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
+			(void *)aup->vaddr, aup->dma_addr);
 
 	iounmap(aup->macdma);
 	iounmap(aup->mac);
diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c
index aec7e98bcc85..96c6f4f36904 100644
--- a/drivers/net/ethernet/i825xx/lasi_82596.c
+++ b/drivers/net/ethernet/i825xx/lasi_82596.c
@@ -96,23 +96,14 @@
 
 #define OPT_SWAP_PORT	0x0001	/* Need to wordswp on the MPU port */
 
-#define LIB82596_DMA_ATTR	DMA_ATTR_NON_CONSISTENT
-
-#define DMA_WBACK(ndev, addr, len) \
-	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_TO_DEVICE); } while (0)
-
-#define DMA_INV(ndev, addr, len) \
-	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_FROM_DEVICE); } while (0)
-
-#define DMA_WBACK_INV(ndev, addr, len) \
-	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_BIDIRECTIONAL); } while (0)
-
 #define SYSBUS      0x0000006c
 
 /* big endian CPU, 82596 "big" endian mode */
 #define SWAP32(x)   (((u32)(x)<<16) | ((((u32)(x)))>>16))
 #define SWAP16(x)   (x)
 
+#define NONCOHERENT_DMA 1
+
 #include "lib82596.c"
 
 MODULE_AUTHOR("Richard Hirst");
@@ -155,7 +146,7 @@ lan_init_chip(struct parisc_device *dev)
 {
 	struct	net_device *netdevice;
 	struct i596_private *lp;
-	int	retval;
+	int retval = -ENOMEM;
 	int i;
 
 	if (!dev->irq) {
@@ -186,12 +177,22 @@ lan_init_chip(struct parisc_device *dev)
 
 	lp = netdev_priv(netdevice);
 	lp->options = dev->id.sversion == 0x72 ? OPT_SWAP_PORT : 0;
+	lp->dma = dma_alloc_noncoherent(&dev->dev,
+			sizeof(struct i596_dma), &lp->dma_addr,
+			DMA_BIDIRECTIONAL, GFP_KERNEL);
+	if (!lp->dma)
+		goto out_free_netdev;
 
 	retval = i82596_probe(netdevice);
-	if (retval) {
-		free_netdev(netdevice);
-		return -ENODEV;
-	}
+	if (retval)
+		goto out_free_dma;
+	return 0;
+
+out_free_dma:
+	dma_free_noncoherent(&dev->dev, sizeof(struct i596_dma),
+		       lp->dma, lp->dma_addr, DMA_BIDIRECTIONAL);
+out_free_netdev:
+	free_netdev(netdevice);
 	return retval;
 }
 
@@ -201,8 +202,8 @@ static int __exit lan_remove_chip(struct parisc_device *pdev)
 	struct i596_private *lp = netdev_priv(dev);
 
 	unregister_netdev (dev);
-	dma_free_attrs(&pdev->dev, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, LIB82596_DMA_ATTR);
+	dma_free_noncoherent(&pdev->dev, sizeof(struct i596_private), lp->dma,
+		       lp->dma_addr, DMA_BIDIRECTIONAL);
 	free_netdev (dev);
 	return 0;
 }
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index b03757e169e4..ca2fb303fcc6 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -365,13 +365,44 @@ static int max_cmd_backlog = TX_RING_SIZE-1;
 static void i596_poll_controller(struct net_device *dev);
 #endif
 
+static inline dma_addr_t virt_to_dma(struct i596_private *lp, volatile void *v)
+{
+	return lp->dma_addr + ((unsigned long)v - (unsigned long)lp->dma);
+}
+
+#ifdef NONCOHERENT_DMA
+static inline void dma_sync_dev(struct net_device *ndev, volatile void *addr,
+		size_t len)
+{
+	dma_sync_single_for_device(ndev->dev.parent,
+			virt_to_dma(netdev_priv(ndev), addr), len,
+			DMA_BIDIRECTIONAL);
+}
+
+static inline void dma_sync_cpu(struct net_device *ndev, volatile void *addr,
+		size_t len)
+{
+	dma_sync_single_for_cpu(ndev->dev.parent,
+			virt_to_dma(netdev_priv(ndev), addr), len,
+			DMA_BIDIRECTIONAL);
+}
+#else
+static inline void dma_sync_dev(struct net_device *ndev, volatile void *addr,
+		size_t len)
+{
+}
+static inline void dma_sync_cpu(struct net_device *ndev, volatile void *addr,
+		size_t len)
+{
+}
+#endif /* NONCOHERENT_DMA */
 
 static inline int wait_istat(struct net_device *dev, struct i596_dma *dma, int delcnt, char *str)
 {
-	DMA_INV(dev, &(dma->iscp), sizeof(struct i596_iscp));
+	dma_sync_cpu(dev, &(dma->iscp), sizeof(struct i596_iscp));
 	while (--delcnt && dma->iscp.stat) {
 		udelay(10);
-		DMA_INV(dev, &(dma->iscp), sizeof(struct i596_iscp));
+		dma_sync_cpu(dev, &(dma->iscp), sizeof(struct i596_iscp));
 	}
 	if (!delcnt) {
 		printk(KERN_ERR "%s: %s, iscp.stat %04x, didn't clear\n",
@@ -384,10 +415,10 @@ static inline int wait_istat(struct net_device *dev, struct i596_dma *dma, int d
 
 static inline int wait_cmd(struct net_device *dev, struct i596_dma *dma, int delcnt, char *str)
 {
-	DMA_INV(dev, &(dma->scb), sizeof(struct i596_scb));
+	dma_sync_cpu(dev, &(dma->scb), sizeof(struct i596_scb));
 	while (--delcnt && dma->scb.command) {
 		udelay(10);
-		DMA_INV(dev, &(dma->scb), sizeof(struct i596_scb));
+		dma_sync_cpu(dev, &(dma->scb), sizeof(struct i596_scb));
 	}
 	if (!delcnt) {
 		printk(KERN_ERR "%s: %s, status %4.4x, cmd %4.4x.\n",
@@ -451,12 +482,9 @@ static void i596_display_data(struct net_device *dev)
 		       SWAP32(rbd->b_data), SWAP16(rbd->size));
 		rbd = rbd->v_next;
 	} while (rbd != lp->rbd_head);
-	DMA_INV(dev, dma, sizeof(struct i596_dma));
+	dma_sync_cpu(dev, dma, sizeof(struct i596_dma));
 }
 
-
-#define virt_to_dma(lp, v) ((lp)->dma_addr + (dma_addr_t)((unsigned long)(v)-(unsigned long)((lp)->dma)))
-
 static inline int init_rx_bufs(struct net_device *dev)
 {
 	struct i596_private *lp = netdev_priv(dev);
@@ -508,7 +536,7 @@ static inline int init_rx_bufs(struct net_device *dev)
 	rfd->b_next = SWAP32(virt_to_dma(lp, dma->rfds));
 	rfd->cmd = SWAP16(CMD_EOL|CMD_FLEX);
 
-	DMA_WBACK_INV(dev, dma, sizeof(struct i596_dma));
+	dma_sync_dev(dev, dma, sizeof(struct i596_dma));
 	return 0;
 }
 
@@ -547,7 +575,7 @@ static void rebuild_rx_bufs(struct net_device *dev)
 	lp->rbd_head = dma->rbds;
 	dma->rfds[0].rbd = SWAP32(virt_to_dma(lp, dma->rbds));
 
-	DMA_WBACK_INV(dev, dma, sizeof(struct i596_dma));
+	dma_sync_dev(dev, dma, sizeof(struct i596_dma));
 }
 
 
@@ -575,9 +603,9 @@ static int init_i596_mem(struct net_device *dev)
 
 	DEB(DEB_INIT, printk(KERN_DEBUG "%s: starting i82596.\n", dev->name));
 
-	DMA_WBACK(dev, &(dma->scp), sizeof(struct i596_scp));
-	DMA_WBACK(dev, &(dma->iscp), sizeof(struct i596_iscp));
-	DMA_WBACK(dev, &(dma->scb), sizeof(struct i596_scb));
+	dma_sync_dev(dev, &(dma->scp), sizeof(struct i596_scp));
+	dma_sync_dev(dev, &(dma->iscp), sizeof(struct i596_iscp));
+	dma_sync_dev(dev, &(dma->scb), sizeof(struct i596_scb));
 
 	mpu_port(dev, PORT_ALTSCP, virt_to_dma(lp, &dma->scp));
 	ca(dev);
@@ -596,24 +624,24 @@ static int init_i596_mem(struct net_device *dev)
 	rebuild_rx_bufs(dev);
 
 	dma->scb.command = 0;
-	DMA_WBACK(dev, &(dma->scb), sizeof(struct i596_scb));
+	dma_sync_dev(dev, &(dma->scb), sizeof(struct i596_scb));
 
 	DEB(DEB_INIT, printk(KERN_DEBUG
 			     "%s: queuing CmdConfigure\n", dev->name));
 	memcpy(dma->cf_cmd.i596_config, init_setup, 14);
 	dma->cf_cmd.cmd.command = SWAP16(CmdConfigure);
-	DMA_WBACK(dev, &(dma->cf_cmd), sizeof(struct cf_cmd));
+	dma_sync_dev(dev, &(dma->cf_cmd), sizeof(struct cf_cmd));
 	i596_add_cmd(dev, &dma->cf_cmd.cmd);
 
 	DEB(DEB_INIT, printk(KERN_DEBUG "%s: queuing CmdSASetup\n", dev->name));
 	memcpy(dma->sa_cmd.eth_addr, dev->dev_addr, ETH_ALEN);
 	dma->sa_cmd.cmd.command = SWAP16(CmdSASetup);
-	DMA_WBACK(dev, &(dma->sa_cmd), sizeof(struct sa_cmd));
+	dma_sync_dev(dev, &(dma->sa_cmd), sizeof(struct sa_cmd));
 	i596_add_cmd(dev, &dma->sa_cmd.cmd);
 
 	DEB(DEB_INIT, printk(KERN_DEBUG "%s: queuing CmdTDR\n", dev->name));
 	dma->tdr_cmd.cmd.command = SWAP16(CmdTDR);
-	DMA_WBACK(dev, &(dma->tdr_cmd), sizeof(struct tdr_cmd));
+	dma_sync_dev(dev, &(dma->tdr_cmd), sizeof(struct tdr_cmd));
 	i596_add_cmd(dev, &dma->tdr_cmd.cmd);
 
 	spin_lock_irqsave (&lp->lock, flags);
@@ -625,7 +653,7 @@ static int init_i596_mem(struct net_device *dev)
 	DEB(DEB_INIT, printk(KERN_DEBUG "%s: Issuing RX_START\n", dev->name));
 	dma->scb.command = SWAP16(RX_START);
 	dma->scb.rfd = SWAP32(virt_to_dma(lp, dma->rfds));
-	DMA_WBACK(dev, &(dma->scb), sizeof(struct i596_scb));
+	dma_sync_dev(dev, &(dma->scb), sizeof(struct i596_scb));
 
 	ca(dev);
 
@@ -659,13 +687,13 @@ static inline int i596_rx(struct net_device *dev)
 
 	rfd = lp->rfd_head;		/* Ref next frame to check */
 
-	DMA_INV(dev, rfd, sizeof(struct i596_rfd));
+	dma_sync_cpu(dev, rfd, sizeof(struct i596_rfd));
 	while (rfd->stat & SWAP16(STAT_C)) {	/* Loop while complete frames */
 		if (rfd->rbd == I596_NULL)
 			rbd = NULL;
 		else if (rfd->rbd == lp->rbd_head->b_addr) {
 			rbd = lp->rbd_head;
-			DMA_INV(dev, rbd, sizeof(struct i596_rbd));
+			dma_sync_cpu(dev, rbd, sizeof(struct i596_rbd));
 		} else {
 			printk(KERN_ERR "%s: rbd chain broken!\n", dev->name);
 			/* XXX Now what? */
@@ -713,7 +741,7 @@ static inline int i596_rx(struct net_device *dev)
 							  DMA_FROM_DEVICE);
 				rbd->v_data = newskb->data;
 				rbd->b_data = SWAP32(dma_addr);
-				DMA_WBACK_INV(dev, rbd, sizeof(struct i596_rbd));
+				dma_sync_dev(dev, rbd, sizeof(struct i596_rbd));
 			} else {
 				skb = netdev_alloc_skb_ip_align(dev, pkt_len);
 			}
@@ -765,7 +793,7 @@ static inline int i596_rx(struct net_device *dev)
 		if (rbd != NULL && (rbd->count & SWAP16(0x4000))) {
 			rbd->count = 0;
 			lp->rbd_head = rbd->v_next;
-			DMA_WBACK_INV(dev, rbd, sizeof(struct i596_rbd));
+			dma_sync_dev(dev, rbd, sizeof(struct i596_rbd));
 		}
 
 		/* Tidy the frame descriptor, marking it as end of list */
@@ -779,14 +807,14 @@ static inline int i596_rx(struct net_device *dev)
 
 		lp->dma->scb.rfd = rfd->b_next;
 		lp->rfd_head = rfd->v_next;
-		DMA_WBACK_INV(dev, rfd, sizeof(struct i596_rfd));
+		dma_sync_dev(dev, rfd, sizeof(struct i596_rfd));
 
 		/* Remove end-of-list from old end descriptor */
 
 		rfd->v_prev->cmd = SWAP16(CMD_FLEX);
-		DMA_WBACK_INV(dev, rfd->v_prev, sizeof(struct i596_rfd));
+		dma_sync_dev(dev, rfd->v_prev, sizeof(struct i596_rfd));
 		rfd = lp->rfd_head;
-		DMA_INV(dev, rfd, sizeof(struct i596_rfd));
+		dma_sync_cpu(dev, rfd, sizeof(struct i596_rfd));
 	}
 
 	DEB(DEB_RXFRAME, printk(KERN_DEBUG "frames %d\n", frames));
@@ -827,12 +855,12 @@ static inline void i596_cleanup_cmd(struct net_device *dev, struct i596_private
 			ptr->v_next = NULL;
 			ptr->b_next = I596_NULL;
 		}
-		DMA_WBACK_INV(dev, ptr, sizeof(struct i596_cmd));
+		dma_sync_dev(dev, ptr, sizeof(struct i596_cmd));
 	}
 
 	wait_cmd(dev, lp->dma, 100, "i596_cleanup_cmd timed out");
 	lp->dma->scb.cmd = I596_NULL;
-	DMA_WBACK(dev, &(lp->dma->scb), sizeof(struct i596_scb));
+	dma_sync_dev(dev, &(lp->dma->scb), sizeof(struct i596_scb));
 }
 
 
@@ -850,7 +878,7 @@ static inline void i596_reset(struct net_device *dev, struct i596_private *lp)
 
 	/* FIXME: this command might cause an lpmc */
 	lp->dma->scb.command = SWAP16(CUC_ABORT | RX_ABORT);
-	DMA_WBACK(dev, &(lp->dma->scb), sizeof(struct i596_scb));
+	dma_sync_dev(dev, &(lp->dma->scb), sizeof(struct i596_scb));
 	ca(dev);
 
 	/* wait for shutdown */
@@ -878,20 +906,20 @@ static void i596_add_cmd(struct net_device *dev, struct i596_cmd *cmd)
 	cmd->command |= SWAP16(CMD_EOL | CMD_INTR);
 	cmd->v_next = NULL;
 	cmd->b_next = I596_NULL;
-	DMA_WBACK(dev, cmd, sizeof(struct i596_cmd));
+	dma_sync_dev(dev, cmd, sizeof(struct i596_cmd));
 
 	spin_lock_irqsave (&lp->lock, flags);
 
 	if (lp->cmd_head != NULL) {
 		lp->cmd_tail->v_next = cmd;
 		lp->cmd_tail->b_next = SWAP32(virt_to_dma(lp, &cmd->status));
-		DMA_WBACK(dev, lp->cmd_tail, sizeof(struct i596_cmd));
+		dma_sync_dev(dev, lp->cmd_tail, sizeof(struct i596_cmd));
 	} else {
 		lp->cmd_head = cmd;
 		wait_cmd(dev, dma, 100, "i596_add_cmd timed out");
 		dma->scb.cmd = SWAP32(virt_to_dma(lp, &cmd->status));
 		dma->scb.command = SWAP16(CUC_START);
-		DMA_WBACK(dev, &(dma->scb), sizeof(struct i596_scb));
+		dma_sync_dev(dev, &(dma->scb), sizeof(struct i596_scb));
 		ca(dev);
 	}
 	lp->cmd_tail = cmd;
@@ -956,7 +984,7 @@ static void i596_tx_timeout (struct net_device *dev, unsigned int txqueue)
 		/* Issue a channel attention signal */
 		DEB(DEB_ERRORS, printk(KERN_DEBUG "Kicking board.\n"));
 		lp->dma->scb.command = SWAP16(CUC_START | RX_START);
-		DMA_WBACK_INV(dev, &(lp->dma->scb), sizeof(struct i596_scb));
+		dma_sync_dev(dev, &(lp->dma->scb), sizeof(struct i596_scb));
 		ca (dev);
 		lp->last_restart = dev->stats.tx_packets;
 	}
@@ -1014,8 +1042,8 @@ static netdev_tx_t i596_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		tbd->data = SWAP32(tx_cmd->dma_addr);
 
 		DEB(DEB_TXADDR, print_eth(skb->data, "tx-queued"));
-		DMA_WBACK_INV(dev, tx_cmd, sizeof(struct tx_cmd));
-		DMA_WBACK_INV(dev, tbd, sizeof(struct i596_tbd));
+		dma_sync_dev(dev, tx_cmd, sizeof(struct tx_cmd));
+		dma_sync_dev(dev, tbd, sizeof(struct i596_tbd));
 		i596_add_cmd(dev, &tx_cmd->cmd);
 
 		dev->stats.tx_packets++;
@@ -1047,9 +1075,8 @@ static const struct net_device_ops i596_netdev_ops = {
 
 static int i82596_probe(struct net_device *dev)
 {
-	int i;
 	struct i596_private *lp = netdev_priv(dev);
-	struct i596_dma *dma;
+	int ret;
 
 	/* This lot is ensure things have been cache line aligned. */
 	BUILD_BUG_ON(sizeof(struct i596_rfd) != 32);
@@ -1063,41 +1090,28 @@ static int i82596_probe(struct net_device *dev)
 	if (!dev->base_addr || !dev->irq)
 		return -ENODEV;
 
-	dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma),
-			      &lp->dma_addr, GFP_KERNEL,
-			      LIB82596_DMA_ATTR);
-	if (!dma) {
-		printk(KERN_ERR "%s: Couldn't get shared memory\n", __FILE__);
-		return -ENOMEM;
-	}
-
 	dev->netdev_ops = &i596_netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 
-	memset(dma, 0, sizeof(struct i596_dma));
-	lp->dma = dma;
-
-	dma->scb.command = 0;
-	dma->scb.cmd = I596_NULL;
-	dma->scb.rfd = I596_NULL;
+	memset(lp->dma, 0, sizeof(struct i596_dma));
+	lp->dma->scb.command = 0;
+	lp->dma->scb.cmd = I596_NULL;
+	lp->dma->scb.rfd = I596_NULL;
 	spin_lock_init(&lp->lock);
 
-	DMA_WBACK_INV(dev, dma, sizeof(struct i596_dma));
+	dma_sync_dev(dev, lp->dma, sizeof(struct i596_dma));
 
-	i = register_netdev(dev);
-	if (i) {
-		dma_free_attrs(dev->dev.parent, sizeof(struct i596_dma),
-			       dma, lp->dma_addr, LIB82596_DMA_ATTR);
-		return i;
-	}
+	ret = register_netdev(dev);
+	if (ret)
+		return ret;
 
 	DEB(DEB_PROBE, printk(KERN_INFO "%s: 82596 at %#3lx, %pM IRQ %d.\n",
 			      dev->name, dev->base_addr, dev->dev_addr,
 			      dev->irq));
 	DEB(DEB_INIT, printk(KERN_INFO
 			     "%s: dma at 0x%p (%d bytes), lp->scb at 0x%p\n",
-			     dev->name, dma, (int)sizeof(struct i596_dma),
-			     &dma->scb));
+			     dev->name, lp->dma, (int)sizeof(struct i596_dma),
+			     &lp->dma->scb));
 
 	return 0;
 }
@@ -1155,7 +1169,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 				   dev->name, status & 0x0700));
 
 		while (lp->cmd_head != NULL) {
-			DMA_INV(dev, lp->cmd_head, sizeof(struct i596_cmd));
+			dma_sync_cpu(dev, lp->cmd_head, sizeof(struct i596_cmd));
 			if (!(lp->cmd_head->status & SWAP16(STAT_C)))
 				break;
 
@@ -1237,7 +1251,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 			}
 			ptr->v_next = NULL;
 			ptr->b_next = I596_NULL;
-			DMA_WBACK(dev, ptr, sizeof(struct i596_cmd));
+			dma_sync_dev(dev, ptr, sizeof(struct i596_cmd));
 			lp->last_cmd = jiffies;
 		}
 
@@ -1251,13 +1265,13 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 
 			ptr->command &= SWAP16(0x1fff);
 			ptr = ptr->v_next;
-			DMA_WBACK_INV(dev, prev, sizeof(struct i596_cmd));
+			dma_sync_dev(dev, prev, sizeof(struct i596_cmd));
 		}
 
 		if (lp->cmd_head != NULL)
 			ack_cmd |= CUC_START;
 		dma->scb.cmd = SWAP32(virt_to_dma(lp, &lp->cmd_head->status));
-		DMA_WBACK_INV(dev, &dma->scb, sizeof(struct i596_scb));
+		dma_sync_dev(dev, &dma->scb, sizeof(struct i596_scb));
 	}
 	if ((status & 0x1000) || (status & 0x4000)) {
 		if ((status & 0x4000))
@@ -1282,7 +1296,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 	}
 	wait_cmd(dev, dma, 100, "i596 interrupt, timeout");
 	dma->scb.command = SWAP16(ack_cmd);
-	DMA_WBACK(dev, &dma->scb, sizeof(struct i596_scb));
+	dma_sync_dev(dev, &dma->scb, sizeof(struct i596_scb));
 
 	/* DANGER: I suspect that some kind of interrupt
 	 acknowledgement aside from acking the 82596 might be needed
@@ -1313,7 +1327,7 @@ static int i596_close(struct net_device *dev)
 
 	wait_cmd(dev, lp->dma, 100, "close1 timed out");
 	lp->dma->scb.command = SWAP16(CUC_ABORT | RX_ABORT);
-	DMA_WBACK(dev, &lp->dma->scb, sizeof(struct i596_scb));
+	dma_sync_dev(dev, &lp->dma->scb, sizeof(struct i596_scb));
 
 	ca(dev);
 
@@ -1372,7 +1386,7 @@ static void set_multicast_list(struct net_device *dev)
 			       dev->name);
 		else {
 			dma->cf_cmd.cmd.command = SWAP16(CmdConfigure);
-			DMA_WBACK_INV(dev, &dma->cf_cmd, sizeof(struct cf_cmd));
+			dma_sync_dev(dev, &dma->cf_cmd, sizeof(struct cf_cmd));
 			i596_add_cmd(dev, &dma->cf_cmd.cmd);
 		}
 	}
@@ -1404,7 +1418,7 @@ static void set_multicast_list(struct net_device *dev)
 					   dev->name, cp));
 			cp += ETH_ALEN;
 		}
-		DMA_WBACK_INV(dev, &dma->mc_cmd, sizeof(struct mc_cmd));
+		dma_sync_dev(dev, &dma->mc_cmd, sizeof(struct mc_cmd));
 		i596_add_cmd(dev, &cmd->cmd);
 	}
 }
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index 22f5887578b2..27937c5d7956 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -24,12 +24,6 @@
 
 static const char sni_82596_string[] = "snirm_82596";
 
-#define LIB82596_DMA_ATTR	0
-
-#define DMA_WBACK(priv, addr, len)     do { } while (0)
-#define DMA_INV(priv, addr, len)       do { } while (0)
-#define DMA_WBACK_INV(priv, addr, len) do { } while (0)
-
 #define SYSBUS      0x00004400
 
 /* big endian CPU, 82596 little endian */
@@ -134,10 +128,19 @@ static int sni_82596_probe(struct platform_device *dev)
 	lp->ca = ca_addr;
 	lp->mpu_port = mpu_addr;
 
-	retval = i82596_probe(netdevice);
-	if (retval == 0)
-		return 0;
+	lp->dma = dma_alloc_coherent(&dev->dev, sizeof(struct i596_dma),
+				     &lp->dma_addr, GFP_KERNEL);
+	if (!lp->dma)
+		goto probe_failed;
 
+	retval = i82596_probe(netdevice);
+	if (retval)
+		goto probe_failed_free_dma;
+	return 0;
+
+probe_failed_free_dma:
+	dma_free_coherent(&dev->dev, sizeof(struct i596_dma), lp->dma,
+			  lp->dma_addr);
 probe_failed:
 	free_netdev(netdevice);
 probe_failed_free_ca:
@@ -153,8 +156,8 @@ static int sni_82596_driver_remove(struct platform_device *pdev)
 	struct i596_private *lp = netdev_priv(dev);
 
 	unregister_netdev(dev);
-	dma_free_attrs(dev->dev.parent, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, LIB82596_DMA_ATTR);
+	dma_free_coherent(&pdev->dev, sizeof(struct i596_private), lp->dma,
+			  lp->dma_addr);
 	iounmap(lp->ca);
 	iounmap(lp->mpu_port);
 	free_netdev (dev);
diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index 8507ff242014..37ff25a84030 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -112,14 +112,18 @@ struct sgiseeq_private {
 
 static inline void dma_sync_desc_cpu(struct net_device *dev, void *addr)
 {
-	dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc),
-		       DMA_FROM_DEVICE);
+	struct sgiseeq_private *sp = netdev_priv(dev);
+
+	dma_sync_single_for_cpu(dev->dev.parent, VIRT_TO_DMA(sp, addr),
+			sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL);
 }
 
 static inline void dma_sync_desc_dev(struct net_device *dev, void *addr)
 {
-	dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc),
-		       DMA_TO_DEVICE);
+	struct sgiseeq_private *sp = netdev_priv(dev);
+
+	dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr),
+			sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL);
 }
 
 static inline void hpc3_eth_reset(struct hpc3_ethregs *hregs)
@@ -403,6 +407,8 @@ static inline void sgiseeq_rx(struct net_device *dev, struct sgiseeq_private *sp
 		rd = &sp->rx_desc[sp->rx_new];
 		dma_sync_desc_cpu(dev, rd);
 	}
+	dma_sync_desc_dev(dev, rd);
+
 	dma_sync_desc_cpu(dev, &sp->rx_desc[orig_end]);
 	sp->rx_desc[orig_end].rdma.cntinfo &= ~(HPCDMA_EOR);
 	dma_sync_desc_dev(dev, &sp->rx_desc[orig_end]);
@@ -443,6 +449,7 @@ static inline void kick_tx(struct net_device *dev,
 		dma_sync_desc_cpu(dev, td);
 	}
 	if (td->tdma.cntinfo & HPCDMA_XIU) {
+		dma_sync_desc_dev(dev, td);
 		hregs->tx_ndptr = VIRT_TO_DMA(sp, td);
 		hregs->tx_ctrl = HPC3_ETXCTRL_ACTIVE;
 	}
@@ -476,6 +483,7 @@ static inline void sgiseeq_tx(struct net_device *dev, struct sgiseeq_private *sp
 		if (!(td->tdma.cntinfo & (HPCDMA_XIU)))
 			break;
 		if (!(td->tdma.cntinfo & (HPCDMA_ETXD))) {
+			dma_sync_desc_dev(dev, td);
 			if (!(status & HPC3_ETXCTRL_ACTIVE)) {
 				hregs->tx_ndptr = VIRT_TO_DMA(sp, td);
 				hregs->tx_ctrl = HPC3_ETXCTRL_ACTIVE;
@@ -740,8 +748,8 @@ static int sgiseeq_probe(struct platform_device *pdev)
 	sp = netdev_priv(dev);
 
 	/* Make private data page aligned */
-	sr = dma_alloc_attrs(&pdev->dev, sizeof(*sp->srings), &sp->srings_dma,
-			     GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
+	sr = dma_alloc_noncoherent(&pdev->dev, sizeof(*sp->srings),
+			&sp->srings_dma, DMA_BIDIRECTIONAL, GFP_KERNEL);
 	if (!sr) {
 		printk(KERN_ERR "Sgiseeq: Page alloc failed, aborting.\n");
 		err = -ENOMEM;
@@ -802,8 +810,8 @@ static int sgiseeq_probe(struct platform_device *pdev)
 	return 0;
 
 err_out_free_attrs:
-	dma_free_attrs(&pdev->dev, sizeof(*sp->srings), sp->srings,
-		       sp->srings_dma, DMA_ATTR_NON_CONSISTENT);
+	dma_free_noncoherent(&pdev->dev, sizeof(*sp->srings), sp->srings,
+		       sp->srings_dma, DMA_BIDIRECTIONAL);
 err_out_free_dev:
 	free_netdev(dev);
 
@@ -817,8 +825,8 @@ static int sgiseeq_remove(struct platform_device *pdev)
 	struct sgiseeq_private *sp = netdev_priv(dev);
 
 	unregister_netdev(dev);
-	dma_free_attrs(&pdev->dev, sizeof(*sp->srings), sp->srings,
-		       sp->srings_dma, DMA_ATTR_NON_CONSISTENT);
+	dma_free_noncoherent(&pdev->dev, sizeof(*sp->srings), sp->srings,
+		       sp->srings_dma, DMA_BIDIRECTIONAL);
 	free_netdev(dev);
 
 	return 0;
diff --git a/drivers/of/address.c b/drivers/of/address.c
index da4f7341323f..eb9ab4f1e80b 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -13,6 +13,7 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 
 #include "of_private.h"
 
@@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 }
 EXPORT_SYMBOL(of_io_request_and_map);
 
+#ifdef CONFIG_HAS_DMA
 /**
- * of_dma_get_range - Get DMA range info
+ * of_dma_get_range - Get DMA range info and put it into a map array
  * @np:		device node to get DMA range info
- * @dma_addr:	pointer to store initial DMA address of DMA range
- * @paddr:	pointer to store initial CPU address of DMA range
- * @size:	pointer to store size of DMA range
+ * @map:	dma range structure to return
  *
  * Look in bottom up direction for the first "dma-ranges" property
- * and parse it.
- *  dma-ranges format:
+ * and parse it.  Put the information into a DMA offset map array.
+ *
+ * dma-ranges format:
  *	DMA addr (dma_addr)	: naddr cells
  *	CPU addr (phys_addr_t)	: pna cells
  *	size			: nsize cells
  *
- * It returns -ENODEV if "dma-ranges" property was not found
- * for this device in DT.
+ * It returns -ENODEV if "dma-ranges" property was not found for this
+ * device in the DT.
  */
-int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 {
 	struct device_node *node = of_node_get(np);
 	const __be32 *ranges = NULL;
-	int len;
-	int ret = 0;
 	bool found_dma_ranges = false;
 	struct of_range_parser parser;
 	struct of_range range;
-	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
+	int len, num_ranges = 0;
+	int ret = 0;
 
 	while (node) {
 		ranges = of_get_property(node, "dma-ranges", &len);
@@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	of_dma_range_parser_init(&parser, node);
+	for_each_of_range(&parser, &range)
+		num_ranges++;
 
+	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * Record all info in the generic DMA ranges array for struct device.
+	 */
+	*map = r;
+	of_dma_range_parser_init(&parser, node);
 	for_each_of_range(&parser, &range) {
 		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
 			 range.bus_addr, range.cpu_addr, range.size);
-
-		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
-			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
-			/* Don't error out as we'd break some existing DTs */
-			continue;
-		}
 		if (range.cpu_addr == OF_BAD_ADDR) {
 			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
 			       range.bus_addr, node);
 			continue;
 		}
-		dma_offset = range.cpu_addr - range.bus_addr;
-
-		/* Take lower and upper limits */
-		if (range.bus_addr < dma_start)
-			dma_start = range.bus_addr;
-		if (range.bus_addr + range.size > dma_end)
-			dma_end = range.bus_addr + range.size;
+		r->cpu_start = range.cpu_addr;
+		r->dma_start = range.bus_addr;
+		r->size = range.size;
+		r->offset = range.cpu_addr - range.bus_addr;
+		r++;
 	}
-
-	if (dma_start >= dma_end) {
-		ret = -EINVAL;
-		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
-			 node);
-		goto out;
-	}
-
-	*dma_addr = dma_start;
-	*size = dma_end - dma_start;
-	*paddr = dma_start + dma_offset;
-
-	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
-		 *dma_addr, *paddr, *size);
-
 out:
 	of_node_put(node);
-
 	return ret;
 }
+#endif /* CONFIG_HAS_DMA */
 
 /**
  * of_dma_is_coherent - Check if device is coherent
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b439c1e05434..655dee422563 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -5,7 +5,8 @@
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -90,14 +91,14 @@ int of_device_add(struct platform_device *ofdev)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	u64 dma_addr, paddr, size = 0;
-	int ret;
-	bool coherent;
-	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask, end;
+	const struct bus_dma_region *map = NULL;
+	dma_addr_t dma_start = 0;
+	u64 mask, end, size = 0;
+	bool coherent;
+	int ret;
 
-	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	ret = of_dma_get_range(np, &map);
 	if (ret < 0) {
 		/*
 		 * For legacy reasons, we have to assume some devices need
@@ -106,26 +107,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		 */
 		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
-
-		dma_addr = offset = 0;
 	} else {
-		offset = PFN_DOWN(paddr - dma_addr);
+		const struct bus_dma_region *r = map;
+		dma_addr_t dma_end = 0;
+
+		/* Determine the overall bounds of all DMA regions */
+		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+			/* Take lower and upper limits */
+			if (r->dma_start < dma_start)
+				dma_start = r->dma_start;
+			if (r->dma_start + r->size > dma_end)
+				dma_end = r->dma_start + r->size;
+		}
+		size = dma_end - dma_start;
 
 		/*
 		 * Add a work around to treat the size as mask + 1 in case
 		 * it is defined in DT as a mask.
 		 */
 		if (size & 1) {
-			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
+			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
 				 size);
 			size = size + 1;
 		}
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
+			kfree(map);
 			return -EINVAL;
 		}
-		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
 
 	/*
@@ -144,13 +154,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	else if (!size)
 		size = 1ULL << 32;
 
-	dev->dma_pfn_offset = offset;
-
 	/*
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	end = dma_addr + size - 1;
+	end = dma_start + size - 1;
 	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
@@ -163,14 +171,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+		kfree(map);
 		return -EPROBE_DEFER;
+	}
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
 
+	dev->dma_range_map = map;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure_id);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index edc682249c00..d9e6a324de0a 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
-#ifdef CONFIG_OF_ADDRESS
-extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-			    u64 *paddr, u64 *size);
+struct bus_dma_region;
+#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
+int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map);
 #else
-static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-				   u64 *paddr, u64 *size)
+static inline int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 9b7e84bdc7d4..06cc988faf78 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -7,6 +7,7 @@
 
 #include <linux/memblock.h>
 #include <linux/clk.h>
+#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
@@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
 }
 
 static void __init of_unittest_dma_ranges_one(const char *path,
-		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
+		u64 expect_dma_addr, u64 expect_paddr)
 {
+#ifdef CONFIG_HAS_DMA
 	struct device_node *np;
-	u64 dma_addr, paddr, size;
+	const struct bus_dma_region *map = NULL;
 	int rc;
 
 	np = of_find_node_by_path(path);
@@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
 		return;
 	}
 
-	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	rc = of_dma_get_range(np, &map);
 
 	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
+
 	if (!rc) {
-		unittest(size == expect_size,
-			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
+		phys_addr_t	paddr;
+		dma_addr_t	dma_addr;
+		struct device	dev_bogus;
+
+		dev_bogus.dma_range_map = map;
+		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
+		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
+
 		unittest(paddr == expect_paddr,
-			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
+			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
+			 &paddr, expect_paddr, np);
 		unittest(dma_addr == expect_dma_addr,
-			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
+			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
+			 &dma_addr, expect_dma_addr, np);
+
+		kfree(map);
 	}
 	of_node_put(np);
+#endif
 }
 
 static void __init of_unittest_parse_dma_ranges(void)
 {
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
-		0x0, 0x20000000, 0x40000000);
+		0x0, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
-		0x100000000, 0x20000000, 0x2000000000);
+		0x100000000, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
-		0x80000000, 0x20000000, 0x10000000);
+		0x80000000, 0x20000000);
 }
 
 static void __init of_unittest_pci_dma_ranges(void)
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index a5507f75b524..b5f9ee81a46c 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -39,6 +39,7 @@
 #include <linux/reboot.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
 #include <linux/export.h>
@@ -356,8 +357,7 @@ ccio_alloc_range(struct ioc *ioc, struct device *dev, size_t size)
 	** ggg sacrifices another 710 to the computer gods.
 	*/
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
 
 	if (pages_needed <= 8) {
 		/*
@@ -1025,6 +1025,8 @@ static const struct dma_map_ops ccio_ops = {
 	.map_sg = 		ccio_map_sg,
 	.unmap_sg = 		ccio_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
+	.alloc_pages =		dma_common_alloc_pages,
+	.free_pages =		dma_common_free_pages,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index d4314fba0269..dce4cdf786cd 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -25,6 +25,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/pci.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
 
@@ -342,8 +343,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	unsigned long shift;
 	int ret;
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
 
 #if defined(ZX1_SUPPORT)
 	BUG_ON(ioc->ibase & ~IOVP_MASK);
@@ -1077,6 +1077,8 @@ static const struct dma_map_ops sba_ops = {
 	.map_sg =		sba_map_sg,
 	.unmap_sg =		sba_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
+	.alloc_pages =		dma_common_alloc_pages,
+	.free_pages =		dma_common_free_pages,
 };
 
 
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 449466f71040..d1b7169c0684 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -19,6 +19,7 @@
 #include <linux/kexec.h>
 #include <linux/of_device.h>
 #include <linux/acpi.h>
+#include <linux/dma-map-ops.h>
 #include "pci.h"
 #include "pcie/portdrv.h"
 
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index c0e85be598c1..c6fe0cfec0f6 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
+#include <linux/swiotlb.h>
 #include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index 09d06b082f8b..72114907c0e4 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -516,7 +516,7 @@ static struct pcmcia_device *pcmcia_device_add(struct pcmcia_socket *s,
 	p_dev->dev.parent = s->dev.parent;
 	p_dev->dev.release = pcmcia_release_dev;
 	/* by default don't allow DMA */
-	p_dev->dma_mask = DMA_MASK_NONE;
+	p_dev->dma_mask = 0;
 	p_dev->dev.dma_mask = &p_dev->dma_mask;
 	dev_set_name(&p_dev->dev, "%d.%d", p_dev->socket->sock, p_dev->device_no);
 	if (!dev_name(&p_dev->dev))
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 7f90eeea67e2..dab2c0f5caf0 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -22,7 +22,9 @@
 #include <linux/device.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
 #include <linux/string.h>
 #include <linux/debugfs.h>
@@ -458,6 +460,25 @@ static void rproc_rvdev_release(struct device *dev)
 	kfree(rvdev);
 }
 
+static int copy_dma_range_map(struct device *to, struct device *from)
+{
+	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
+	int num_ranges = 0;
+
+	if (!map)
+		return 0;
+
+	for (r = map; r->size; r++)
+		num_ranges++;
+
+	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
+			  GFP_KERNEL);
+	if (!new_map)
+		return -ENOMEM;
+	to->dma_range_map = new_map;
+	return 0;
+}
+
 /**
  * rproc_handle_vdev() - handle a vdev fw resource
  * @rproc: the remote processor
@@ -529,7 +550,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 	/* Initialise vdev subdevice */
 	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
 	rvdev->dev.parent = &rproc->dev;
-	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
+	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
+	if (ret)
+		return ret;
 	rvdev->dev.release = rproc_rvdev_release;
 	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
 	dev_set_drvdata(&rvdev->dev, rvdev);
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index dfd3808c34fd..0cc617f76068 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -9,7 +9,7 @@
  * Brian Swetland <swetland@google.com>
  */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/remoteproc.h>
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 84b57a8f86bf..5117d90ccd9e 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -269,6 +269,27 @@ NCR_700_get_SXFER(struct scsi_device *SDp)
 					      spi_period(SDp->sdev_target));
 }
 
+static inline dma_addr_t virt_to_dma(struct NCR_700_Host_Parameters *h, void *p)
+{
+	return h->pScript + ((uintptr_t)p - (uintptr_t)h->script);
+}
+
+static inline void dma_sync_to_dev(struct NCR_700_Host_Parameters *h,
+		void *addr, size_t size)
+{
+	if (h->noncoherent)
+		dma_sync_single_for_device(h->dev, virt_to_dma(h, addr),
+					   size, DMA_BIDIRECTIONAL);
+}
+
+static inline void dma_sync_from_dev(struct NCR_700_Host_Parameters *h,
+		void *addr, size_t size)
+{
+	if (h->noncoherent)
+		dma_sync_single_for_device(h->dev, virt_to_dma(h, addr), size,
+					   DMA_BIDIRECTIONAL);
+}
+
 struct Scsi_Host *
 NCR_700_detect(struct scsi_host_template *tpnt,
 	       struct NCR_700_Host_Parameters *hostdata, struct device *dev)
@@ -283,9 +304,13 @@ NCR_700_detect(struct scsi_host_template *tpnt,
 	if(tpnt->sdev_attrs == NULL)
 		tpnt->sdev_attrs = NCR_700_dev_attrs;
 
-	memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript,
-				 GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
-	if(memory == NULL) {
+	memory = dma_alloc_coherent(dev, TOTAL_MEM_SIZE, &pScript, GFP_KERNEL);
+	if (!memory) {
+		hostdata->noncoherent = 1;
+		memory = dma_alloc_noncoherent(dev, TOTAL_MEM_SIZE, &pScript,
+					 DMA_BIDIRECTIONAL, GFP_KERNEL);
+	}
+	if (!memory) {
 		printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n");
 		return NULL;
 	}
@@ -339,11 +364,11 @@ NCR_700_detect(struct scsi_host_template *tpnt,
 	for (j = 0; j < PATCHES; j++)
 		script[LABELPATCHES[j]] = bS_to_host(pScript + SCRIPT[LABELPATCHES[j]]);
 	/* now patch up fixed addresses. */
-	script_patch_32(hostdata->dev, script, MessageLocation,
+	script_patch_32(hostdata, script, MessageLocation,
 			pScript + MSGOUT_OFFSET);
-	script_patch_32(hostdata->dev, script, StatusAddress,
+	script_patch_32(hostdata, script, StatusAddress,
 			pScript + STATUS_OFFSET);
-	script_patch_32(hostdata->dev, script, ReceiveMsgAddress,
+	script_patch_32(hostdata, script, ReceiveMsgAddress,
 			pScript + MSGIN_OFFSET);
 
 	hostdata->script = script;
@@ -395,8 +420,13 @@ NCR_700_release(struct Scsi_Host *host)
 	struct NCR_700_Host_Parameters *hostdata = 
 		(struct NCR_700_Host_Parameters *)host->hostdata[0];
 
-	dma_free_attrs(hostdata->dev, TOTAL_MEM_SIZE, hostdata->script,
-		       hostdata->pScript, DMA_ATTR_NON_CONSISTENT);
+	if (hostdata->noncoherent)
+		dma_free_noncoherent(hostdata->dev, TOTAL_MEM_SIZE,
+				hostdata->script, hostdata->pScript,
+				DMA_BIDIRECTIONAL);
+	else
+		dma_free_coherent(hostdata->dev, TOTAL_MEM_SIZE,
+				  hostdata->script, hostdata->pScript);
 	return 1;
 }
 
@@ -804,8 +834,8 @@ process_extended_message(struct Scsi_Host *host,
 			shost_printk(KERN_WARNING, host,
 				"Unexpected SDTR msg\n");
 			hostdata->msgout[0] = A_REJECT_MSG;
-			dma_cache_sync(hostdata->dev, hostdata->msgout, 1, DMA_TO_DEVICE);
-			script_patch_16(hostdata->dev, hostdata->script,
+			dma_sync_to_dev(hostdata, hostdata->msgout, 1);
+			script_patch_16(hostdata, hostdata->script,
 			                MessageCount, 1);
 			/* SendMsgOut returns, so set up the return
 			 * address */
@@ -817,9 +847,8 @@ process_extended_message(struct Scsi_Host *host,
 		printk(KERN_INFO "scsi%d: (%d:%d), Unsolicited WDTR after CMD, Rejecting\n",
 		       host->host_no, pun, lun);
 		hostdata->msgout[0] = A_REJECT_MSG;
-		dma_cache_sync(hostdata->dev, hostdata->msgout, 1, DMA_TO_DEVICE);
-		script_patch_16(hostdata->dev, hostdata->script, MessageCount,
-		                1);
+		dma_sync_to_dev(hostdata, hostdata->msgout, 1);
+		script_patch_16(hostdata, hostdata->script, MessageCount, 1);
 		resume_offset = hostdata->pScript + Ent_SendMessageWithATN;
 
 		break;
@@ -832,9 +861,8 @@ process_extended_message(struct Scsi_Host *host,
 		printk("\n");
 		/* just reject it */
 		hostdata->msgout[0] = A_REJECT_MSG;
-		dma_cache_sync(hostdata->dev, hostdata->msgout, 1, DMA_TO_DEVICE);
-		script_patch_16(hostdata->dev, hostdata->script, MessageCount,
-		                1);
+		dma_sync_to_dev(hostdata, hostdata->msgout, 1);
+		script_patch_16(hostdata, hostdata->script, MessageCount, 1);
 		/* SendMsgOut returns, so set up the return
 		 * address */
 		resume_offset = hostdata->pScript + Ent_SendMessageWithATN;
@@ -917,9 +945,8 @@ process_message(struct Scsi_Host *host,	struct NCR_700_Host_Parameters *hostdata
 		printk("\n");
 		/* just reject it */
 		hostdata->msgout[0] = A_REJECT_MSG;
-		dma_cache_sync(hostdata->dev, hostdata->msgout, 1, DMA_TO_DEVICE);
-		script_patch_16(hostdata->dev, hostdata->script, MessageCount,
-		                1);
+		dma_sync_to_dev(hostdata, hostdata->msgout, 1);
+		script_patch_16(hostdata, hostdata->script, MessageCount, 1);
 		/* SendMsgOut returns, so set up the return
 		 * address */
 		resume_offset = hostdata->pScript + Ent_SendMessageWithATN;
@@ -928,7 +955,7 @@ process_message(struct Scsi_Host *host,	struct NCR_700_Host_Parameters *hostdata
 	}
 	NCR_700_writel(temp, host, TEMP_REG);
 	/* set us up to receive another message */
-	dma_cache_sync(hostdata->dev, hostdata->msgin, MSG_ARRAY_SIZE, DMA_FROM_DEVICE);
+	dma_sync_from_dev(hostdata, hostdata->msgin, MSG_ARRAY_SIZE);
 	return resume_offset;
 }
 
@@ -1008,8 +1035,8 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
 				slot->SG[1].ins = bS_to_host(SCRIPT_RETURN);
 				slot->SG[1].pAddr = 0;
 				slot->resume_offset = hostdata->pScript;
-				dma_cache_sync(hostdata->dev, slot->SG, sizeof(slot->SG[0])*2, DMA_TO_DEVICE);
-				dma_cache_sync(hostdata->dev, SCp->sense_buffer, SCSI_SENSE_BUFFERSIZE, DMA_FROM_DEVICE);
+				dma_sync_to_dev(hostdata, slot->SG, sizeof(slot->SG[0])*2);
+				dma_sync_from_dev(hostdata, SCp->sense_buffer, SCSI_SENSE_BUFFERSIZE);
 
 				/* queue the command for reissue */
 				slot->state = NCR_700_SLOT_QUEUED;
@@ -1129,11 +1156,11 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
 			hostdata->cmd = slot->cmnd;
 
 			/* re-patch for this command */
-			script_patch_32_abs(hostdata->dev, hostdata->script,
+			script_patch_32_abs(hostdata, hostdata->script,
 			                    CommandAddress, slot->pCmd);
-			script_patch_16(hostdata->dev, hostdata->script,
+			script_patch_16(hostdata, hostdata->script,
 					CommandCount, slot->cmnd->cmd_len);
-			script_patch_32_abs(hostdata->dev, hostdata->script,
+			script_patch_32_abs(hostdata, hostdata->script,
 			                    SGScriptStartAddress,
 					    to32bit(&slot->pSG[0].ins));
 
@@ -1144,14 +1171,14 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
 			 * should therefore always clear ACK */
 			NCR_700_writeb(NCR_700_get_SXFER(hostdata->cmd->device),
 				       host, SXFER_REG);
-			dma_cache_sync(hostdata->dev, hostdata->msgin,
-				       MSG_ARRAY_SIZE, DMA_FROM_DEVICE);
-			dma_cache_sync(hostdata->dev, hostdata->msgout,
-				       MSG_ARRAY_SIZE, DMA_TO_DEVICE);
+			dma_sync_from_dev(hostdata, hostdata->msgin,
+				       MSG_ARRAY_SIZE);
+			dma_sync_to_dev(hostdata, hostdata->msgout,
+				       MSG_ARRAY_SIZE);
 			/* I'm just being paranoid here, the command should
 			 * already have been flushed from the cache */
-			dma_cache_sync(hostdata->dev, slot->cmnd->cmnd,
-				       slot->cmnd->cmd_len, DMA_TO_DEVICE);
+			dma_sync_to_dev(hostdata, slot->cmnd->cmnd,
+				       slot->cmnd->cmd_len);
 
 
 			
@@ -1214,8 +1241,7 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
 		hostdata->reselection_id = reselection_id;
 		/* just in case we have a stale simple tag message, clear it */
 		hostdata->msgin[1] = 0;
-		dma_cache_sync(hostdata->dev, hostdata->msgin,
-			       MSG_ARRAY_SIZE, DMA_BIDIRECTIONAL);
+		dma_sync_to_dev(hostdata, hostdata->msgin, MSG_ARRAY_SIZE);
 		if(hostdata->tag_negotiated & (1<<reselection_id)) {
 			resume_offset = hostdata->pScript + Ent_GetReselectionWithTag;
 		} else {
@@ -1329,8 +1355,7 @@ process_selection(struct Scsi_Host *host, __u32 dsp)
 	hostdata->cmd = NULL;
 	/* clear any stale simple tag message */
 	hostdata->msgin[1] = 0;
-	dma_cache_sync(hostdata->dev, hostdata->msgin, MSG_ARRAY_SIZE,
-		       DMA_BIDIRECTIONAL);
+	dma_sync_to_dev(hostdata, hostdata->msgin, MSG_ARRAY_SIZE);
 
 	if(id == 0xff) {
 		/* Selected as target, Ignore */
@@ -1427,30 +1452,26 @@ NCR_700_start_command(struct scsi_cmnd *SCp)
 		NCR_700_set_flag(SCp->device, NCR_700_DEV_BEGIN_SYNC_NEGOTIATION);
 	}
 
-	script_patch_16(hostdata->dev, hostdata->script, MessageCount, count);
+	script_patch_16(hostdata, hostdata->script, MessageCount, count);
 
+	script_patch_ID(hostdata, hostdata->script, Device_ID, 1<<scmd_id(SCp));
 
-	script_patch_ID(hostdata->dev, hostdata->script,
-			Device_ID, 1<<scmd_id(SCp));
-
-	script_patch_32_abs(hostdata->dev, hostdata->script, CommandAddress,
+	script_patch_32_abs(hostdata, hostdata->script, CommandAddress,
 			    slot->pCmd);
-	script_patch_16(hostdata->dev, hostdata->script, CommandCount,
-	                SCp->cmd_len);
+	script_patch_16(hostdata, hostdata->script, CommandCount, SCp->cmd_len);
 	/* finally plumb the beginning of the SG list into the script
 	 * */
-	script_patch_32_abs(hostdata->dev, hostdata->script,
+	script_patch_32_abs(hostdata, hostdata->script,
 	                    SGScriptStartAddress, to32bit(&slot->pSG[0].ins));
 	NCR_700_clear_fifo(SCp->device->host);
 
 	if(slot->resume_offset == 0)
 		slot->resume_offset = hostdata->pScript;
 	/* now perform all the writebacks and invalidates */
-	dma_cache_sync(hostdata->dev, hostdata->msgout, count, DMA_TO_DEVICE);
-	dma_cache_sync(hostdata->dev, hostdata->msgin, MSG_ARRAY_SIZE,
-		       DMA_FROM_DEVICE);
-	dma_cache_sync(hostdata->dev, SCp->cmnd, SCp->cmd_len, DMA_TO_DEVICE);
-	dma_cache_sync(hostdata->dev, hostdata->status, 1, DMA_FROM_DEVICE);
+	dma_sync_to_dev(hostdata, hostdata->msgout, count);
+	dma_sync_from_dev(hostdata, hostdata->msgin, MSG_ARRAY_SIZE);
+	dma_sync_to_dev(hostdata, SCp->cmnd, SCp->cmd_len);
+	dma_sync_from_dev(hostdata, hostdata->status, 1);
 
 	/* set the synchronous period/offset */
 	NCR_700_writeb(NCR_700_get_SXFER(SCp->device),
@@ -1626,7 +1647,7 @@ NCR_700_intr(int irq, void *dev_id)
 					slot->SG[i].ins = bS_to_host(SCRIPT_NOP);
 					slot->SG[i].pAddr = 0;
 				}
-				dma_cache_sync(hostdata->dev, slot->SG, sizeof(slot->SG), DMA_TO_DEVICE);
+				dma_sync_to_dev(hostdata, slot->SG, sizeof(slot->SG));
 				/* and pretend we disconnected after
 				 * the command phase */
 				resume_offset = hostdata->pScript + Ent_MsgInDuringData;
@@ -1878,7 +1899,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 		}
 		slot->SG[i].ins = bS_to_host(SCRIPT_RETURN);
 		slot->SG[i].pAddr = 0;
-		dma_cache_sync(hostdata->dev, slot->SG, sizeof(slot->SG), DMA_TO_DEVICE);
+		dma_sync_to_dev(hostdata, slot->SG, sizeof(slot->SG));
 		DEBUG((" SETTING %p to %x\n",
 		       (&slot->pSG[i].ins),
 		       slot->SG[i].ins));
diff --git a/drivers/scsi/53c700.h b/drivers/scsi/53c700.h
index 05fe439b66af..c9f8c497babb 100644
--- a/drivers/scsi/53c700.h
+++ b/drivers/scsi/53c700.h
@@ -209,6 +209,7 @@ struct NCR_700_Host_Parameters {
 #endif
 	__u32	chip710:1;	/* set if really a 710 not 700 */
 	__u32	burst_length:4;	/* set to 0 to disable 710 bursting */
+	__u32	noncoherent:1;	/* needs to use non-coherent DMA */
 
 	/* NOTHING BELOW HERE NEEDS ALTERING */
 	__u32	fast:1;		/* if we can alter the SCSI bus clock
@@ -422,33 +423,33 @@ struct NCR_700_Host_Parameters {
 #define NCR_710_MIN_XFERP	0
 #define NCR_700_MIN_PERIOD	25 /* for SDTR message, 100ns */
 
-#define script_patch_32(dev, script, symbol, value) \
+#define script_patch_32(h, script, symbol, value) \
 { \
 	int i; \
 	dma_addr_t da = value; \
 	for(i=0; i< (sizeof(A_##symbol##_used) / sizeof(__u32)); i++) { \
 		__u32 val = bS_to_cpu((script)[A_##symbol##_used[i]]) + da; \
 		(script)[A_##symbol##_used[i]] = bS_to_host(val); \
-		dma_cache_sync((dev), &(script)[A_##symbol##_used[i]], 4, DMA_TO_DEVICE); \
+		dma_sync_to_dev((h), &(script)[A_##symbol##_used[i]], 4); \
 		DEBUG((" script, patching %s at %d to %pad\n", \
 		       #symbol, A_##symbol##_used[i], &da)); \
 	} \
 }
 
-#define script_patch_32_abs(dev, script, symbol, value) \
+#define script_patch_32_abs(h, script, symbol, value) \
 { \
 	int i; \
 	dma_addr_t da = value; \
 	for(i=0; i< (sizeof(A_##symbol##_used) / sizeof(__u32)); i++) { \
 		(script)[A_##symbol##_used[i]] = bS_to_host(da); \
-		dma_cache_sync((dev), &(script)[A_##symbol##_used[i]], 4, DMA_TO_DEVICE); \
+		dma_sync_to_dev((h), &(script)[A_##symbol##_used[i]], 4); \
 		DEBUG((" script, patching %s at %d to %pad\n", \
 		       #symbol, A_##symbol##_used[i], &da)); \
 	} \
 }
 
 /* Used for patching the SCSI ID in the SELECT instruction */
-#define script_patch_ID(dev, script, symbol, value) \
+#define script_patch_ID(h, script, symbol, value) \
 { \
 	int i; \
 	for(i=0; i< (sizeof(A_##symbol##_used) / sizeof(__u32)); i++) { \
@@ -456,13 +457,13 @@ struct NCR_700_Host_Parameters {
 		val &= 0xff00ffff; \
 		val |= ((value) & 0xff) << 16; \
 		(script)[A_##symbol##_used[i]] = bS_to_host(val); \
-		dma_cache_sync((dev), &(script)[A_##symbol##_used[i]], 4, DMA_TO_DEVICE); \
+		dma_sync_to_dev((h), &(script)[A_##symbol##_used[i]], 4); \
 		DEBUG((" script, patching ID field %s at %d to 0x%x\n", \
 		       #symbol, A_##symbol##_used[i], val)); \
 	} \
 }
 
-#define script_patch_16(dev, script, symbol, value) \
+#define script_patch_16(h, script, symbol, value) \
 { \
 	int i; \
 	for(i=0; i< (sizeof(A_##symbol##_used) / sizeof(__u32)); i++) { \
@@ -470,7 +471,7 @@ struct NCR_700_Host_Parameters {
 		val &= 0xffff0000; \
 		val |= ((value) & 0xffff); \
 		(script)[A_##symbol##_used[i]] = bS_to_host(val); \
-		dma_cache_sync((dev), &(script)[A_##symbol##_used[i]], 4, DMA_TO_DEVICE); \
+		dma_sync_to_dev((h), &(script)[A_##symbol##_used[i]], 4); \
 		DEBUG((" script, patching short field %s at %d to 0x%x\n", \
 		       #symbol, A_##symbol##_used[i], val)); \
 	} \
diff --git a/drivers/scsi/sgiwd93.c b/drivers/scsi/sgiwd93.c
index 3bdf0deb8f15..cf1030c9dda1 100644
--- a/drivers/scsi/sgiwd93.c
+++ b/drivers/scsi/sgiwd93.c
@@ -95,7 +95,7 @@ void fill_hpc_entries(struct ip22_hostdata *hd, struct scsi_cmnd *cmd, int din)
 	 */
 	hcp->desc.pbuf = 0;
 	hcp->desc.cntinfo = HPCDMA_EOX;
-	dma_cache_sync(hd->dev, hd->cpu,
+	dma_sync_single_for_device(hd->dev, hd->dma,
 		       (unsigned long)(hcp + 1) - (unsigned long)hd->cpu,
 		       DMA_TO_DEVICE);
 }
@@ -234,8 +234,8 @@ static int sgiwd93_probe(struct platform_device *pdev)
 
 	hdata = host_to_hostdata(host);
 	hdata->dev = &pdev->dev;
-	hdata->cpu = dma_alloc_attrs(&pdev->dev, HPC_DMA_SIZE, &hdata->dma,
-				     GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
+	hdata->cpu = dma_alloc_noncoherent(&pdev->dev, HPC_DMA_SIZE,
+				&hdata->dma, DMA_TO_DEVICE, GFP_KERNEL);
 	if (!hdata->cpu) {
 		printk(KERN_WARNING "sgiwd93: Could not allocate memory for "
 		       "host %d buffer.\n", unit);
@@ -274,8 +274,8 @@ static int sgiwd93_probe(struct platform_device *pdev)
 out_irq:
 	free_irq(irq, host);
 out_free:
-	dma_free_attrs(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma,
-		       DMA_ATTR_NON_CONSISTENT);
+	dma_free_noncoherent(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma,
+			DMA_TO_DEVICE);
 out_put:
 	scsi_host_put(host);
 out:
@@ -291,8 +291,8 @@ static int sgiwd93_remove(struct platform_device *pdev)
 
 	scsi_remove_host(host);
 	free_irq(pd->irq, host);
-	dma_free_attrs(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma,
-		       DMA_ATTR_NON_CONSISTENT);
+	dma_free_noncoherent(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma,
+			DMA_TO_DEVICE);
 	scsi_host_put(host);
 	return 0;
 }
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
index 1744e6fcc999..bcf050a04ffc 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
@@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
 	 * the RAM offset to the physcal addresses.
 	 *
 	 * This information will eventually be obtained from device-tree.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
 	 */
 
 #ifdef PHYS_PFN_OFFSET
-	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
-		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
+		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
+	}
 #endif
 
 	ret = of_reserved_mem_device_init(dev->dev);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index f4107b9e8c38..19ebb542befc 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -2087,12 +2087,6 @@ int usb_set_configuration(struct usb_device *dev, int configuration)
 		intf->dev.bus = &usb_bus_type;
 		intf->dev.type = &usb_if_device_type;
 		intf->dev.groups = usb_interface_groups;
-		/*
-		 * Please refer to usb_alloc_dev() to see why we set
-		 * dma_mask and dma_pfn_offset.
-		 */
-		intf->dev.dma_mask = dev->dev.dma_mask;
-		intf->dev.dma_pfn_offset = dev->dev.dma_pfn_offset;
 		INIT_WORK(&intf->reset_ws, __usb_queue_reset_device);
 		intf->minor = -1;
 		device_initialize(&intf->dev);
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index bafc113f2b3e..9b4ac4415f1a 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -599,18 +599,6 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent,
 	dev->dev.bus = &usb_bus_type;
 	dev->dev.type = &usb_device_type;
 	dev->dev.groups = usb_device_groups;
-	/*
-	 * Fake a dma_mask/offset for the USB device:
-	 * We cannot really use the dma-mapping API (dma_alloc_* and
-	 * dma_map_*) for USB devices but instead need to use
-	 * usb_alloc_coherent and pass data in 'urb's, but some subsystems
-	 * manually look into the mask/offset pair to determine whether
-	 * they need bounce buffers.
-	 * Note: calling dma_set_mask() on a USB device would set the
-	 * mask for the entire HCD, so don't do that.
-	 */
-	dev->dev.dma_mask = bus->sysdev->dma_mask;
-	dev->dev.dma_pfn_offset = bus->sysdev->dma_pfn_offset;
 	set_dev_node(&dev->dev, dev_to_node(bus->sysdev));
 	dev->state = USB_STATE_ATTACHED;
 	dev->lpm_disable_count = 1;
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 62d640327145..2629911c29bb 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -18,7 +18,7 @@
 #include <linux/wait.h>
 #include <linux/uuid.h>
 #include <linux/iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sysfs.h>
 #include <linux/file.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 39a0f2e0847c..71ce1b7a23d1 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -28,7 +28,7 @@
 
 #include <linux/memblock.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <xen/swiotlb-xen.h>
 #include <xen/page.h>
@@ -578,4 +578,6 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.dma_supported = xen_swiotlb_dma_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 74b0612601dd..62ebdc731ee2 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -16,7 +16,6 @@ mandatory-y += current.h
 mandatory-y += delay.h
 mandatory-y += device.h
 mandatory-y += div64.h
-mandatory-y += dma-contiguous.h
 mandatory-y += dma-mapping.h
 mandatory-y += dma.h
 mandatory-y += emergency-restart.h
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
deleted file mode 100644
index f24b0f9a4f05..000000000000
--- a/include/asm-generic/dma-contiguous.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
-#define _ASM_GENERIC_DMA_CONTIGUOUS_H
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 6ff79fefd01f..217999c8a762 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -18,6 +18,8 @@
 
 #endif
 
+#define CMA_MAX_NAME 64
+
 struct cma;
 
 extern unsigned long totalcma_pages;
diff --git a/include/linux/device.h b/include/linux/device.h
index a8e3a86e35f6..5ed101be7b2e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -413,7 +413,7 @@ struct dev_links_info {
  * 		such descriptors.
  * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
  *		DMA limit than the device itself supports.
- * @dma_pfn_offset: offset of DMA memory range relatively of RAM
+ * @dma_range_map: map for DMA memory ranges relative to that of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
  * @dma_pools:	Dma pools (if dma'ble device).
@@ -508,7 +508,7 @@ struct device {
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
 	u64		bus_dma_limit;	/* upstream dma constraint */
-	unsigned long	dma_pfn_offset;
+	const struct bus_dma_region *dma_range_map;
 
 	struct device_dma_parameters *dma_parms;
 
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
deleted file mode 100644
index 03f8e98e3bcc..000000000000
--- a/include/linux/dma-contiguous.h
+++ /dev/null
@@ -1,176 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef __LINUX_CMA_H
-#define __LINUX_CMA_H
-
-/*
- * Contiguous Memory Allocator for DMA mapping framework
- * Copyright (c) 2010-2011 by Samsung Electronics.
- * Written by:
- *	Marek Szyprowski <m.szyprowski@samsung.com>
- *	Michal Nazarewicz <mina86@mina86.com>
- */
-
-/*
- * Contiguous Memory Allocator
- *
- *   The Contiguous Memory Allocator (CMA) makes it possible to
- *   allocate big contiguous chunks of memory after the system has
- *   booted.
- *
- * Why is it needed?
- *
- *   Various devices on embedded systems have no scatter-getter and/or
- *   IO map support and require contiguous blocks of memory to
- *   operate.  They include devices such as cameras, hardware video
- *   coders, etc.
- *
- *   Such devices often require big memory buffers (a full HD frame
- *   is, for instance, more then 2 mega pixels large, i.e. more than 6
- *   MB of memory), which makes mechanisms such as kmalloc() or
- *   alloc_page() ineffective.
- *
- *   At the same time, a solution where a big memory region is
- *   reserved for a device is suboptimal since often more memory is
- *   reserved then strictly required and, moreover, the memory is
- *   inaccessible to page system even if device drivers don't use it.
- *
- *   CMA tries to solve this issue by operating on memory regions
- *   where only movable pages can be allocated from.  This way, kernel
- *   can use the memory for pagecache and when device driver requests
- *   it, allocated pages can be migrated.
- *
- * Driver usage
- *
- *   CMA should not be used by the device drivers directly. It is
- *   only a helper framework for dma-mapping subsystem.
- *
- *   For more information, see kernel-docs in kernel/dma/contiguous.c
- */
-
-#ifdef __KERNEL__
-
-#include <linux/device.h>
-#include <linux/mm.h>
-
-struct cma;
-struct page;
-
-#ifdef CONFIG_DMA_CMA
-
-extern struct cma *dma_contiguous_default_area;
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	if (dev && dev->cma_area)
-		return dev->cma_area;
-	return dma_contiguous_default_area;
-}
-
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
-{
-	if (dev)
-		dev->cma_area = cma;
-}
-
-static inline void dma_contiguous_set_default(struct cma *cma)
-{
-	dma_contiguous_default_area = cma;
-}
-
-void dma_contiguous_reserve(phys_addr_t addr_limit);
-
-int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma,
-				       bool fixed);
-
-/**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- *			      for particular device
- * @dev:   Pointer to device structure.
- * @size:  Size of the reserved memory.
- * @base:  Start address of the reserved memory (optional, 0 for any).
- * @limit: End address of the reserved memory (optional, 0 for any).
- *
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
- */
-
-static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-					 phys_addr_t base, phys_addr_t limit)
-{
-	struct cma *cma;
-	int ret;
-	ret = dma_contiguous_reserve_area(size, base, limit, &cma, true);
-	if (ret == 0)
-		dev_set_cma_area(dev, cma);
-
-	return ret;
-}
-
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order, bool no_warn);
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
-				 int count);
-struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
-void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
-
-#else
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	return NULL;
-}
-
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { }
-
-static inline void dma_contiguous_set_default(struct cma *cma) { }
-
-static inline void dma_contiguous_reserve(phys_addr_t limit) { }
-
-static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma,
-				       bool fixed)
-{
-	return -ENOSYS;
-}
-
-static inline
-int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-			   phys_addr_t base, phys_addr_t limit)
-{
-	return -ENOSYS;
-}
-
-static inline
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order, bool no_warn)
-{
-	return NULL;
-}
-
-static inline
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
-				 int count)
-{
-	return false;
-}
-
-/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
-static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
-		gfp_t gfp)
-{
-	return NULL;
-}
-
-static inline void dma_free_contiguous(struct device *dev, struct page *page,
-		size_t size)
-{
-	__free_pages(page, get_order(size));
-}
-
-#endif
-
-#endif
-
-#endif
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 6e87225600ae..18aade195884 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -7,28 +7,83 @@
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
 #include <linux/swiotlb.h>
 
 extern unsigned int zone_dma_bits;
 
-#ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
-#include <asm/dma-direct.h>
-#else
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	dma_addr_t dev_addr = (dma_addr_t)paddr;
+/*
+ * Record the mapping of CPU physical to DMA addresses for a given region.
+ */
+struct bus_dma_region {
+	phys_addr_t	cpu_start;
+	dma_addr_t	dma_start;
+	u64		size;
+	u64		offset;
+};
 
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+static inline dma_addr_t translate_phys_to_dma(struct device *dev,
+		phys_addr_t paddr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
+			return (dma_addr_t)paddr - m->offset;
+
+	/* make sure dma_capable fails when no translation is available */
+	return DMA_MAPPING_ERROR;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t translate_dma_to_phys(struct device *dev,
+		dma_addr_t dma_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr;
+	const struct bus_dma_region *m;
 
-	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	for (m = dev->dma_range_map; m->size; m++)
+		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
+			return (phys_addr_t)dma_addr + m->offset;
+
+	return (phys_addr_t)-1;
+}
+
+#ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
+#include <asm/dma-direct.h>
+#ifndef phys_to_dma_unencrypted
+#define phys_to_dma_unencrypted		phys_to_dma
+#endif
+#else
+static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
+		phys_addr_t paddr)
+{
+	if (dev->dma_range_map)
+		return translate_phys_to_dma(dev, paddr);
+	return paddr;
+}
+
+/*
+ * If memory encryption is supported, phys_to_dma will set the memory encryption
+ * bit in the DMA address, and dma_to_phys will clear it.
+ * phys_to_dma_unencrypted is for use on special unencrypted memory like swiotlb
+ * buffers.
+ */
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	phys_addr_t paddr;
+
+	if (dev->dma_range_map)
+		paddr = translate_dma_to_phys(dev, dma_addr);
+	else
+		paddr = dma_addr;
+
+	return __sme_clr(paddr);
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
@@ -41,30 +96,13 @@ static inline bool force_dma_unencrypted(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 
-/*
- * If memory encryption is supported, phys_to_dma will set the memory encryption
- * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
- * and __dma_to_phys versions should only be used on non-encrypted memory for
- * special occasions like DMA coherent buffers.
- */
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return __sme_set(__phys_to_dma(dev, paddr));
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return __sme_clr(__dma_to_phys(dev, daddr));
-}
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 		bool is_ram)
 {
 	dma_addr_t end = addr + size - 1;
 
-	if (!dev->dma_mask)
+	if (addr == DMA_MAPPING_ERROR)
 		return false;
-
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
@@ -77,115 +115,13 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
-void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs);
-int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-bool dma_direct_can_mmap(struct device *dev);
-int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir);
 int dma_direct_supported(struct device *dev, u64 mask);
-bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
-size_t dma_direct_max_mapping_size(struct device *dev);
 
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_sg(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(paddr, size, dir);
-}
-
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(paddr, size, dir);
-		arch_sync_dma_for_cpu_all();
-	}
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-}
-
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
-	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
-		return swiotlb_map(dev, phys, size, dir, attrs);
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
-	}
-
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(phys, size, dir);
-	return dma_addr;
-}
-
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = dma_to_phys(dev, addr);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h
index 9c96e30e6a0b..a2fe4571bc92 100644
--- a/include/linux/dma-direction.h
+++ b/include/linux/dma-direction.h
@@ -9,4 +9,10 @@ enum dma_data_direction {
 	DMA_NONE = 3,
 };
 
-#endif
+static inline int valid_dma_direction(enum dma_data_direction dir)
+{
+	return dir == DMA_BIDIRECTIONAL || dir == DMA_TO_DEVICE ||
+		dir == DMA_FROM_DEVICE;
+}
+
+#endif /* _LINUX_DMA_DIRECTION_H */
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
new file mode 100644
index 000000000000..8029f7e04145
--- /dev/null
+++ b/include/linux/dma-map-ops.h
@@ -0,0 +1,326 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This header is for implementations of dma_map_ops and related code.
+ * It should not be included in drivers just using the DMA API.
+ */
+#ifndef _LINUX_DMA_MAP_OPS_H
+#define _LINUX_DMA_MAP_OPS_H
+
+#include <linux/dma-mapping.h>
+#include <linux/pgtable.h>
+
+struct cma;
+
+struct dma_map_ops {
+	void *(*alloc)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, gfp_t gfp,
+			unsigned long attrs);
+	void (*free)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, unsigned long attrs);
+	struct page *(*alloc_pages)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
+	void *(*alloc_noncoherent)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
+	int (*mmap)(struct device *, struct vm_area_struct *,
+			void *, dma_addr_t, size_t, unsigned long attrs);
+
+	int (*get_sgtable)(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			unsigned long attrs);
+
+	dma_addr_t (*map_page)(struct device *dev, struct page *page,
+			unsigned long offset, size_t size,
+			enum dma_data_direction dir, unsigned long attrs);
+	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	/*
+	 * map_sg returns 0 on error and a value > 0 on success.
+	 * It should never return a value < 0.
+	 */
+	int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, unsigned long attrs);
+	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, unsigned long attrs);
+	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir);
+	void (*sync_single_for_device)(struct device *dev,
+			dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction dir);
+	void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir);
+	void (*sync_sg_for_device)(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir);
+	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
+			enum dma_data_direction direction);
+	int (*dma_supported)(struct device *dev, u64 mask);
+	u64 (*get_required_mask)(struct device *dev);
+	size_t (*max_mapping_size)(struct device *dev);
+	unsigned long (*get_merge_boundary)(struct device *dev);
+};
+
+#ifdef CONFIG_DMA_OPS
+#include <asm/dma-mapping.h>
+
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (dev->dma_ops)
+		return dev->dma_ops;
+	return get_arch_dma_ops(dev->bus);
+}
+
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+	dev->dma_ops = dma_ops;
+}
+#else /* CONFIG_DMA_OPS */
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return NULL;
+}
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+}
+#endif /* CONFIG_DMA_OPS */
+
+#ifdef CONFIG_DMA_CMA
+extern struct cma *dma_contiguous_default_area;
+
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+void dma_contiguous_reserve(phys_addr_t addr_limit);
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+		phys_addr_t limit, struct cma **res_cma, bool fixed);
+
+struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
+				       unsigned int order, bool no_warn);
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count);
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
+#else /* CONFIG_DMA_CMA */
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	return NULL;
+}
+static inline void dma_contiguous_reserve(phys_addr_t limit)
+{
+}
+static inline int dma_contiguous_reserve_area(phys_addr_t size,
+		phys_addr_t base, phys_addr_t limit, struct cma **res_cma,
+		bool fixed)
+{
+	return -ENOSYS;
+}
+static inline struct page *dma_alloc_from_contiguous(struct device *dev,
+		size_t count, unsigned int order, bool no_warn)
+{
+	return NULL;
+}
+static inline bool dma_release_from_contiguous(struct device *dev,
+		struct page *pages, int count)
+{
+	return false;
+}
+/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
+static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
+		gfp_t gfp)
+{
+	return NULL;
+}
+static inline void dma_free_contiguous(struct device *dev, struct page *page,
+		size_t size)
+{
+	__free_pages(page, get_order(size));
+}
+#endif /* CONFIG_DMA_CMA*/
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void dma_pernuma_cma_reserve(void);
+#else
+static inline void dma_pernuma_cma_reserve(void) { }
+#endif /* CONFIG_DMA_PERNUMA_CMA */
+
+#ifdef CONFIG_DMA_DECLARE_COHERENT
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+		dma_addr_t device_addr, size_t size);
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle, void **ret);
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, size_t size, int *ret);
+
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle);
+int dma_release_from_global_coherent(int order, void *vaddr);
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
+		size_t size, int *ret);
+
+#else
+static inline int dma_declare_coherent_memory(struct device *dev,
+		phys_addr_t phys_addr, dma_addr_t device_addr, size_t size)
+{
+	return -ENOSYS;
+}
+#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
+
+static inline void *dma_alloc_from_global_coherent(struct device *dev,
+		ssize_t size, dma_addr_t *dma_handle)
+{
+	return NULL;
+}
+static inline int dma_release_from_global_coherent(int order, void *vaddr)
+{
+	return 0;
+}
+static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
+		void *cpu_addr, size_t size, int *ret)
+{
+	return 0;
+}
+#endif /* CONFIG_DMA_DECLARE_COHERENT */
+
+#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
+#include <asm/dma-coherence.h>
+#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
+static inline bool dev_is_dma_coherent(struct device *dev)
+{
+	return dev->dma_coherent;
+}
+#else
+static inline bool dev_is_dma_coherent(struct device *dev)
+{
+	return true;
+}
+#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs);
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs);
+
+#ifdef CONFIG_MMU
+/*
+ * Page protection so that devices that can't snoop CPU caches can use the
+ * memory coherently.  We default to pgprot_noncached which is usually used
+ * for ioremap as a safe bet, but architectures can override this with less
+ * strict semantics if possible.
+ */
+#ifndef pgprot_dmacoherent
+#define pgprot_dmacoherent(prot)	pgprot_noncached(prot)
+#endif
+
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
+#else
+static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
+		unsigned long attrs)
+{
+	return prot;	/* no protection bits supported without page tables */
+}
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(void);
+#else
+static inline void arch_sync_dma_for_cpu_all(void)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
+#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
+void arch_dma_prep_coherent(struct page *page, size_t size);
+#else
+static inline void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+}
+#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
+
+#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
+#else
+static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
+{
+}
+#endif /* ARCH_HAS_DMA_MARK_CLEAN */
+
+void *arch_dma_set_uncached(void *addr, size_t size);
+void arch_dma_clear_uncached(void *addr, size_t size);
+
+#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+		const struct iommu_ops *iommu, bool coherent);
+#else
+static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
+		u64 size, const struct iommu_ops *iommu, bool coherent)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
+
+#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS
+void arch_teardown_dma_ops(struct device *dev);
+#else
+static inline void arch_teardown_dma_ops(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
+
+#ifdef CONFIG_DMA_API_DEBUG
+void dma_debug_add_bus(struct bus_type *bus);
+void debug_dma_dump_mappings(struct device *dev);
+#else
+static inline void dma_debug_add_bus(struct bus_type *bus)
+{
+}
+static inline void debug_dma_dump_mappings(struct device *dev)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+
+extern const struct dma_map_ops dma_dummy_ops;
+
+#endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 52635e91143b..3f029afdc9dc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -6,7 +6,6 @@
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/err.h>
-#include <linux/dma-debug.h>
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
 #include <linux/bug.h>
@@ -27,11 +26,6 @@
  * buffered to improve performance.
  */
 #define DMA_ATTR_WRITE_COMBINE		(1UL << 2)
-/*
- * DMA_ATTR_NON_CONSISTENT: Lets the platform to choose to return either
- * consistent or non-consistent memory as it sees fit.
- */
-#define DMA_ATTR_NON_CONSISTENT		(1UL << 3)
 /*
  * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel
  * virtual mapping for the allocated buffer.
@@ -68,153 +62,35 @@
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
 /*
- * A dma_addr_t can hold any valid DMA or bus address for the platform.
- * It can be given to a device to use as a DMA source or target.  A CPU cannot
- * reference a dma_addr_t directly because there may be translation between
- * its physical address space and the bus address space.
+ * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
+ * be given to a device to use as a DMA source or target.  It is specific to a
+ * given device and there may be a translation between the CPU physical address
+ * space and the bus address space.
+ *
+ * DMA_MAPPING_ERROR is the magic error code if a mapping failed.  It should not
+ * be used directly in drivers, but checked for using dma_mapping_error()
+ * instead.
  */
-struct dma_map_ops {
-	void* (*alloc)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t gfp,
-				unsigned long attrs);
-	void (*free)(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle,
-			      unsigned long attrs);
-	int (*mmap)(struct device *, struct vm_area_struct *,
-			  void *, dma_addr_t, size_t,
-			  unsigned long attrs);
-
-	int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *,
-			   dma_addr_t, size_t, unsigned long attrs);
-
-	dma_addr_t (*map_page)(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction dir,
-			       unsigned long attrs);
-	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir,
-			   unsigned long attrs);
-	/*
-	 * map_sg returns 0 on error and a value > 0 on success.
-	 * It should never return a value < 0.
-	 */
-	int (*map_sg)(struct device *dev, struct scatterlist *sg,
-		      int nents, enum dma_data_direction dir,
-		      unsigned long attrs);
-	void (*unmap_sg)(struct device *dev,
-			 struct scatterlist *sg, int nents,
-			 enum dma_data_direction dir,
-			 unsigned long attrs);
-	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs);
-	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir,
-			   unsigned long attrs);
-	void (*sync_single_for_cpu)(struct device *dev,
-				    dma_addr_t dma_handle, size_t size,
-				    enum dma_data_direction dir);
-	void (*sync_single_for_device)(struct device *dev,
-				       dma_addr_t dma_handle, size_t size,
-				       enum dma_data_direction dir);
-	void (*sync_sg_for_cpu)(struct device *dev,
-				struct scatterlist *sg, int nents,
-				enum dma_data_direction dir);
-	void (*sync_sg_for_device)(struct device *dev,
-				   struct scatterlist *sg, int nents,
-				   enum dma_data_direction dir);
-	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
-			enum dma_data_direction direction);
-	int (*dma_supported)(struct device *dev, u64 mask);
-	u64 (*get_required_mask)(struct device *dev);
-	size_t (*max_mapping_size)(struct device *dev);
-	unsigned long (*get_merge_boundary)(struct device *dev);
-};
-
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
-extern const struct dma_map_ops dma_virt_ops;
-extern const struct dma_map_ops dma_dummy_ops;
-
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-#define DMA_MASK_NONE	0x0ULL
-
-static inline int valid_dma_direction(int dma_direction)
-{
-	return ((dma_direction == DMA_BIDIRECTIONAL) ||
-		(dma_direction == DMA_TO_DEVICE) ||
-		(dma_direction == DMA_FROM_DEVICE));
-}
-
-#ifdef CONFIG_DMA_DECLARE_COHERENT
-/*
- * These three functions are only for dma allocator.
- * Don't use them in device drivers.
- */
-int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret);
-int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
-
-int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
-			    void *cpu_addr, size_t size, int *ret);
-
-void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle);
-int dma_release_from_global_coherent(int order, void *vaddr);
-int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
-				  size_t size, int *ret);
-
+#ifdef CONFIG_DMA_API_DEBUG
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len);
 #else
-#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
-#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
-#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
-
-static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
-						   dma_addr_t *dma_handle)
+static inline void debug_dma_mapping_error(struct device *dev,
+		dma_addr_t dma_addr)
 {
-	return NULL;
 }
-
-static inline int dma_release_from_global_coherent(int order, void *vaddr)
+static inline void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len)
 {
-	return 0;
 }
-
-static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
-						void *cpu_addr, size_t size,
-						int *ret)
-{
-	return 0;
-}
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
+#endif /* CONFIG_DMA_API_DEBUG */
 
 #ifdef CONFIG_HAS_DMA
-#include <asm/dma-mapping.h>
-
-#ifdef CONFIG_DMA_OPS
-static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
-{
-	if (dev->dma_ops)
-		return dev->dma_ops;
-	return get_arch_dma_ops(dev->bus);
-}
-
-static inline void set_dma_ops(struct device *dev,
-			       const struct dma_map_ops *dma_ops)
-{
-	dev->dma_ops = dma_ops;
-}
-#else /* CONFIG_DMA_OPS */
-static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
-{
-	return NULL;
-}
-static inline void set_dma_ops(struct device *dev,
-			       const struct dma_map_ops *dma_ops)
-{
-}
-#endif /* CONFIG_DMA_OPS */
-
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	debug_dma_mapping_error(dev, dma_addr);
@@ -254,8 +130,6 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle);
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir);
 int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
@@ -339,10 +213,6 @@ static inline void dmam_free_coherent(struct device *dev, size_t size,
 		void *vaddr, dma_addr_t dma_handle)
 {
 }
-static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
 static inline int dma_get_sgtable_attrs(struct device *dev,
 		struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr,
 		size_t size, unsigned long attrs)
@@ -389,6 +259,15 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 }
 #endif /* CONFIG_HAS_DMA */
 
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
@@ -513,7 +392,10 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
-
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
 struct page **dma_common_find_pages(void *cpu_addr);
 void *dma_common_contiguous_remap(struct page *page, size_t size,
 			pgprot_t prot, const void *caller);
@@ -591,24 +473,6 @@ static inline bool dma_addressing_limited(struct device *dev)
 			    dma_get_required_mask(dev);
 }
 
-#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
-#else
-static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
-
-#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS
-void arch_teardown_dma_ops(struct device *dev);
-#else
-static inline void arch_teardown_dma_ops(struct device *dev)
-{
-}
-#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
-
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->max_segment_size)
@@ -629,7 +493,26 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->segment_boundary_mask)
 		return dev->dma_parms->segment_boundary_mask;
-	return DMA_BIT_MASK(32);
+	return ULONG_MAX;
+}
+
+/**
+ * dma_get_seg_boundary_nr_pages - return the segment boundary in "page" units
+ * @dev: device to guery the boundary for
+ * @page_shift: ilog() of the IOMMU page size
+ *
+ * Return the segment boundary in IOMMU page units (which may be different from
+ * the CPU page size) for the passed in device.
+ *
+ * If @dev is NULL a boundary of U32_MAX is assumed, this case is just for
+ * non-DMA API callers.
+ */
+static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev,
+		unsigned int page_shift)
+{
+	if (!dev)
+		return (U32_MAX >> page_shift) + 1;
+	return (dma_get_seg_boundary(dev) >> page_shift) + 1;
 }
 
 static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
@@ -649,18 +532,6 @@ static inline int dma_get_cache_alignment(void)
 	return 1;
 }
 
-#ifdef CONFIG_DMA_DECLARE_COHERENT
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				dma_addr_t device_addr, size_t size);
-#else
-static inline int
-dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-			    dma_addr_t device_addr, size_t size)
-{
-	return -ENOSYS;
-}
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
-
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
@@ -711,4 +582,13 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
 #endif
 
-#endif
+/*
+ * Legacy interface to set up the dma offset map.  Drivers really should not
+ * actually use it, but we have a few legacy cases left.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+		dma_addr_t dma_start, u64 size);
+
+extern const struct dma_map_ops dma_virt_ops;
+
+#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
deleted file mode 100644
index ca09a4e07d2d..000000000000
--- a/include/linux/dma-noncoherent.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_DMA_NONCOHERENT_H
-#define _LINUX_DMA_NONCOHERENT_H 1
-
-#include <linux/dma-mapping.h>
-#include <linux/pgtable.h>
-
-#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
-#include <asm/dma-coherence.h>
-#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-static inline bool dev_is_dma_coherent(struct device *dev)
-{
-	return dev->dma_coherent;
-}
-#else
-static inline bool dev_is_dma_coherent(struct device *dev)
-{
-	return true;
-}
-#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
-
-/*
- * Check if an allocation needs to be marked uncached to be coherent.
- */
-static __always_inline bool dma_alloc_need_uncached(struct device *dev,
-		unsigned long attrs)
-{
-	if (dev_is_dma_coherent(dev))
-		return false;
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
-		return false;
-	if (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
-	    (attrs & DMA_ATTR_NON_CONSISTENT))
-		return false;
-	return true;
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs);
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs);
-
-#ifdef CONFIG_MMU
-/*
- * Page protection so that devices that can't snoop CPU caches can use the
- * memory coherently.  We default to pgprot_noncached which is usually used
- * for ioremap as a safe bet, but architectures can override this with less
- * strict semantics if possible.
- */
-#ifndef pgprot_dmacoherent
-#define pgprot_dmacoherent(prot)	pgprot_noncached(prot)
-#endif
-
-pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
-#else
-static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
-		unsigned long attrs)
-{
-	return prot;	/* no protection bits supported without page tables */
-}
-#endif /* CONFIG_MMU */
-
-#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction);
-#else
-static inline void arch_dma_cache_sync(struct device *dev, void *vaddr,
-		size_t size, enum dma_data_direction direction)
-{
-}
-#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
-void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir);
-#else
-static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
-#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir);
-#else
-static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
-#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
-void arch_sync_dma_for_cpu_all(void);
-#else
-static inline void arch_sync_dma_for_cpu_all(void)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
-
-#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
-void arch_dma_prep_coherent(struct page *page, size_t size);
-#else
-static inline void arch_dma_prep_coherent(struct page *page, size_t size)
-{
-}
-#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
-
-void *arch_dma_set_uncached(void *addr, size_t size);
-void arch_dma_clear_uncached(void *addr, size_t size);
-
-#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 07e481993ef5..c603237e006c 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -552,8 +552,10 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
 	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
 #else
-#define alloc_pages(gfp_mask, order) \
-		alloc_pages_node(numa_node_id(), gfp_mask, order)
+static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+	return alloc_pages_node(numa_node_id(), gfp_mask, order);
+}
 #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
 	alloc_pages(gfp_mask, order)
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 847a9d1fa634..c99de4a21458 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -9,6 +9,7 @@ config HAS_DMA
 	default y
 
 config DMA_OPS
+	depends on HAS_DMA
 	bool
 
 #
@@ -43,6 +44,12 @@ config ARCH_HAS_DMA_SET_MASK
 config ARCH_HAS_DMA_WRITE_COMBINE
 	bool
 
+#
+# Select if the architectures provides the arch_dma_mark_clean hook
+#
+config ARCH_HAS_DMA_MARK_CLEAN
+	bool
+
 config DMA_DECLARE_COHERENT
 	bool
 
@@ -68,9 +75,6 @@ config ARCH_HAS_DMA_PREP_COHERENT
 config ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	bool
 
-config DMA_NONCOHERENT_CACHE_SYNC
-	bool
-
 config DMA_VIRT_OPS
 	bool
 	depends on HAS_DMA
@@ -114,10 +118,21 @@ config DMA_CMA
 	  You can disable CMA by specifying "cma=0" on the kernel's command
 	  line.
 
-	  For more information see <include/linux/dma-contiguous.h>.
+	  For more information see <kernel/dma/contiguous.c>.
 	  If unsure, say "n".
 
 if  DMA_CMA
+
+config DMA_PERNUMA_CMA
+	bool "Enable separate DMA Contiguous Memory Area for each NUMA Node"
+	default NUMA && ARM64
+	help
+	  Enable this option to get pernuma CMA areas so that devices like
+	  ARM64 SMMU can get local memory by DMA coherent APIs.
+
+	  You can set the size of pernuma CMA by specifying "cma_pernuma=size"
+	  on the kernel's command line.
+
 comment "Default contiguous memory area size:"
 
 config CMA_SIZE_MBYTES
@@ -162,7 +177,7 @@ endchoice
 
 config CMA_ALIGNMENT
 	int "Maximum PAGE_SIZE order of alignment for contiguous buffers"
-	range 4 12
+	range 2 12
 	default 8
 	help
 	  DMA mapping framework by default aligns all buffers to the smallest
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
index 32c7c1942bbd..dc755ab68aab 100644
--- a/kernel/dma/Makefile
+++ b/kernel/dma/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o
+obj-$(CONFIG_DMA_OPS)			+= ops_helpers.o
 obj-$(CONFIG_DMA_OPS)			+= dummy.o
 obj-$(CONFIG_DMA_CMA)			+= contiguous.o
 obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 2a0c4985f38e..5b5b6c7ec7f2 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -7,7 +7,8 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
@@ -32,9 +33,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
 					     struct dma_coherent_mem * mem)
 {
 	if (mem->use_dev_dma_pfn_offset)
-		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
-	else
-		return mem->device_base;
+		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
+	return mem->device_base;
 }
 
 static int dma_init_coherent_memory(phys_addr_t phys_addr,
@@ -107,6 +107,23 @@ static int dma_assign_coherent_memory(struct device *dev,
 	return 0;
 }
 
+/*
+ * Declare a region of memory to be handed out by dma_alloc_coherent() when it
+ * is asked for coherent memory for this device.  This shall only be used
+ * from platform code, usually based on the device tree description.
+ * 
+ * phys_addr is the CPU physical address to which the memory is currently
+ * assigned (this will be ioremapped so the CPU can access the region).
+ *
+ * device_addr is the DMA address the device needs to be programmed with to
+ * actually address this memory (this will be handed out as the dma_addr_t in
+ * dma_alloc_coherent()).
+ *
+ * size is the size of the area (must be a multiple of PAGE_SIZE).
+ *
+ * As a simplification for the platforms, only *one* such region of memory may
+ * be declared per device.
+ */
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 				dma_addr_t device_addr, size_t size)
 {
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 0369fd5fda8f..16b95ff12e4d 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -5,6 +5,34 @@
  * Written by:
  *	Marek Szyprowski <m.szyprowski@samsung.com>
  *	Michal Nazarewicz <mina86@mina86.com>
+ *
+ * Contiguous Memory Allocator
+ *
+ *   The Contiguous Memory Allocator (CMA) makes it possible to
+ *   allocate big contiguous chunks of memory after the system has
+ *   booted.
+ *
+ * Why is it needed?
+ *
+ *   Various devices on embedded systems have no scatter-getter and/or
+ *   IO map support and require contiguous blocks of memory to
+ *   operate.  They include devices such as cameras, hardware video
+ *   coders, etc.
+ *
+ *   Such devices often require big memory buffers (a full HD frame
+ *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   MB of memory), which makes mechanisms such as kmalloc() or
+ *   alloc_page() ineffective.
+ *
+ *   At the same time, a solution where a big memory region is
+ *   reserved for a device is suboptimal since often more memory is
+ *   reserved then strictly required and, moreover, the memory is
+ *   inaccessible to page system even if device drivers don't use it.
+ *
+ *   CMA tries to solve this issue by operating on memory regions
+ *   where only movable pages can be allocated from.  This way, kernel
+ *   can use the memory for pagecache and when device driver requests
+ *   it, allocated pages can be migrated.
  */
 
 #define pr_fmt(fmt) "cma: " fmt
@@ -16,12 +44,11 @@
 #endif
 
 #include <asm/page.h>
-#include <asm/dma-contiguous.h>
 
 #include <linux/memblock.h>
 #include <linux/err.h>
 #include <linux/sizes.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/cma.h>
 
 #ifdef CONFIG_CMA_SIZE_MBYTES
@@ -69,6 +96,19 @@ static int __init early_cma(char *p)
 }
 early_param("cma", early_cma);
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+
+static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES];
+static phys_addr_t pernuma_size_bytes __initdata;
+
+static int __init early_cma_pernuma(char *p)
+{
+	pernuma_size_bytes = memparse(p, &p);
+	return 0;
+}
+early_param("cma_pernuma", early_cma_pernuma);
+#endif
+
 #ifdef CONFIG_CMA_SIZE_PERCENTAGE
 
 static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
@@ -87,6 +127,34 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 
 #endif
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void __init dma_pernuma_cma_reserve(void)
+{
+	int nid;
+
+	if (!pernuma_size_bytes)
+		return;
+
+	for_each_online_node(nid) {
+		int ret;
+		char name[CMA_MAX_NAME];
+		struct cma **cma = &dma_contiguous_pernuma_area[nid];
+
+		snprintf(name, sizeof(name), "pernuma%d", nid);
+		ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0,
+						 0, false, name, cma, nid);
+		if (ret) {
+			pr_warn("%s: reservation failed: err %d, node %d", __func__,
+				ret, nid);
+			continue;
+		}
+
+		pr_debug("%s: reserved %llu MiB on node %d\n", __func__,
+			(unsigned long long)pernuma_size_bytes / SZ_1M, nid);
+	}
+}
+#endif
+
 /**
  * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
  * @limit: End address of the reserved memory (optional, 0 for any).
@@ -134,6 +202,11 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	}
 }
 
+void __weak
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
+
 /**
  * dma_contiguous_reserve_area() - reserve custom contiguous area
  * @size: Size of the reserved area (in bytes),
@@ -219,23 +292,44 @@ static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
  * @size:  Requested allocation size.
  * @gfp:   Allocation flags.
  *
- * This function allocates contiguous memory buffer for specified device. It
- * tries to use device specific contiguous memory area if available, or the
- * default global one.
+ * tries to use device specific contiguous memory area if available, or it
+ * tries to use per-numa cma, if the allocation fails, it will fallback to
+ * try default global one.
  *
- * Note that it byapss one-page size of allocations from the global area as
- * the addresses within one page are always contiguous, so there is no need
- * to waste CMA pages for that kind; it also helps reduce fragmentations.
+ * Note that it bypass one-page size of allocations from the per-numa and
+ * global area as the addresses within one page are always contiguous, so
+ * there is no need to waste CMA pages for that kind; it also helps reduce
+ * fragmentations.
  */
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	int nid = dev_to_node(dev);
+#endif
+
 	/* CMA can be used only in the context which permits sleeping */
 	if (!gfpflags_allow_blocking(gfp))
 		return NULL;
 	if (dev->cma_area)
 		return cma_alloc_aligned(dev->cma_area, size, gfp);
-	if (size <= PAGE_SIZE || !dma_contiguous_default_area)
+	if (size <= PAGE_SIZE)
 		return NULL;
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	if (nid != NUMA_NO_NODE && !(gfp & (GFP_DMA | GFP_DMA32))) {
+		struct cma *cma = dma_contiguous_pernuma_area[nid];
+		struct page *page;
+
+		if (cma) {
+			page = cma_alloc_aligned(cma, size, gfp);
+			if (page)
+				return page;
+		}
+	}
+#endif
+	if (!dma_contiguous_default_area)
+		return NULL;
+
 	return cma_alloc_aligned(dma_contiguous_default_area, size, gfp);
 }
 
@@ -252,9 +346,27 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
  */
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 {
-	if (!cma_release(dev_get_cma_area(dev), page,
-			 PAGE_ALIGN(size) >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	/* if dev has its own cma, free page from there */
+	if (dev->cma_area) {
+		if (cma_release(dev->cma_area, page, count))
+			return;
+	} else {
+		/*
+		 * otherwise, page is from either per-numa cma or default cma
+		 */
+#ifdef CONFIG_DMA_PERNUMA_CMA
+		if (cma_release(dma_contiguous_pernuma_area[page_to_nid(page)],
+					page, count))
+			return;
+#endif
+		if (cma_release(dma_contiguous_default_area, page, count))
+			return;
+	}
+
+	/* not in any cma, free from buddy */
+	__free_pages(page, get_order(size));
 }
 
 /*
@@ -270,14 +382,14 @@ void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 
 static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	dev_set_cma_area(dev, rmem->priv);
+	dev->cma_area = rmem->priv;
 	return 0;
 }
 
 static void rmem_cma_device_release(struct reserved_mem *rmem,
 				    struct device *dev)
 {
-	dev_set_cma_area(dev, NULL);
+	dev->cma_area = NULL;
 }
 
 static const struct reserved_mem_ops rmem_cma_ops = {
@@ -318,7 +430,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
-		dma_contiguous_set_default(cma);
+		dma_contiguous_default_area = cma;
 
 	rmem->ops = &rmem_cma_ops;
 	rmem->priv = cma;
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 8e9f7b301c6d..14de1271463f 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -9,10 +9,9 @@
 
 #include <linux/sched/task_stack.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sched/task.h>
 #include <linux/stacktrace.h>
-#include <linux/dma-debug.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/debugfs.h>
@@ -24,8 +23,8 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
-
 #include <asm/sections.h>
+#include "debug.h"
 
 #define HASH_SIZE       16384ULL
 #define HASH_FN_SHIFT   13
@@ -1219,7 +1218,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 	entry->dev       = dev;
 	entry->type      = dma_debug_single;
 	entry->pfn	 = page_to_pfn(page);
-	entry->offset	 = offset,
+	entry->offset	 = offset;
 	entry->dev_addr  = dma_addr;
 	entry->size      = size;
 	entry->direction = direction;
@@ -1235,7 +1234,6 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 
 	add_dma_entry(entry);
 }
-EXPORT_SYMBOL(debug_dma_map_page);
 
 void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -1290,7 +1288,6 @@ void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
 		return;
 	check_unmap(&ref);
 }
-EXPORT_SYMBOL(debug_dma_unmap_page);
 
 void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		      int nents, int mapped_ents, int direction)
@@ -1310,7 +1307,7 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		entry->type           = dma_debug_sg;
 		entry->dev            = dev;
 		entry->pfn	      = page_to_pfn(sg_page(s));
-		entry->offset	      = s->offset,
+		entry->offset	      = s->offset;
 		entry->size           = sg_dma_len(s);
 		entry->dev_addr       = sg_dma_address(s);
 		entry->direction      = direction;
@@ -1328,7 +1325,6 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		add_dma_entry(entry);
 	}
 }
-EXPORT_SYMBOL(debug_dma_map_sg);
 
 static int get_nr_mapped_entries(struct device *dev,
 				 struct dma_debug_entry *ref)
@@ -1380,7 +1376,6 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		check_unmap(&ref);
 	}
 }
-EXPORT_SYMBOL(debug_dma_unmap_sg);
 
 void debug_dma_alloc_coherent(struct device *dev, size_t size,
 			      dma_addr_t dma_addr, void *virt)
@@ -1466,7 +1461,6 @@ void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
 
 	add_dma_entry(entry);
 }
-EXPORT_SYMBOL(debug_dma_map_resource);
 
 void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
 			      size_t size, int direction)
@@ -1484,7 +1478,6 @@ void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
 
 	check_unmap(&ref);
 }
-EXPORT_SYMBOL(debug_dma_unmap_resource);
 
 void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				   size_t size, int direction)
@@ -1503,7 +1496,6 @@ void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 
 	check_sync(dev, &ref, true);
 }
-EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
 
 void debug_dma_sync_single_for_device(struct device *dev,
 				      dma_addr_t dma_handle, size_t size,
@@ -1523,7 +1515,6 @@ void debug_dma_sync_single_for_device(struct device *dev,
 
 	check_sync(dev, &ref, false);
 }
-EXPORT_SYMBOL(debug_dma_sync_single_for_device);
 
 void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 			       int nelems, int direction)
@@ -1556,7 +1547,6 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 		check_sync(dev, &ref, true);
 	}
 }
-EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
 
 void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 				  int nelems, int direction)
@@ -1588,7 +1578,6 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 		check_sync(dev, &ref, false);
 	}
 }
-EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
 
 static int __init dma_debug_driver_setup(char *str)
 {
diff --git a/include/linux/dma-debug.h b/kernel/dma/debug.h
similarity index 81%
rename from include/linux/dma-debug.h
rename to kernel/dma/debug.h
index 7b3b04ba60f3..83643b3010b2 100644
--- a/include/linux/dma-debug.h
+++ b/kernel/dma/debug.h
@@ -5,28 +5,14 @@
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  */
 
-#ifndef __DMA_DEBUG_H
-#define __DMA_DEBUG_H
-
-#include <linux/types.h>
-
-struct device;
-struct scatterlist;
-struct bus_type;
+#ifndef _KERNEL_DMA_DEBUG_H
+#define _KERNEL_DMA_DEBUG_H
 
 #ifdef CONFIG_DMA_API_DEBUG
-
-extern void dma_debug_add_bus(struct bus_type *bus);
-
-extern void debug_dma_map_single(struct device *dev, const void *addr,
-				 unsigned long len);
-
 extern void debug_dma_map_page(struct device *dev, struct page *page,
 			       size_t offset, size_t size,
 			       int direction, dma_addr_t dma_addr);
 
-extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
 extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
 				 size_t size, int direction);
 
@@ -64,31 +50,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev,
 extern void debug_dma_sync_sg_for_device(struct device *dev,
 					 struct scatterlist *sg,
 					 int nelems, int direction);
-
-extern void debug_dma_dump_mappings(struct device *dev);
-
 #else /* CONFIG_DMA_API_DEBUG */
-
-static inline void dma_debug_add_bus(struct bus_type *bus)
-{
-}
-
-static inline void debug_dma_map_single(struct device *dev, const void *addr,
-					unsigned long len)
-{
-}
-
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
 				      size_t offset, size_t size,
 				      int direction, dma_addr_t dma_addr)
 {
 }
 
-static inline void debug_dma_mapping_error(struct device *dev,
-					  dma_addr_t dma_addr)
-{
-}
-
 static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
 					size_t size, int direction)
 {
@@ -150,11 +118,5 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev,
 						int nelems, int direction)
 {
 }
-
-static inline void debug_dma_dump_mappings(struct device *dev)
-{
-}
-
 #endif /* CONFIG_DMA_API_DEBUG */
-
-#endif /* __DMA_DEBUG_H */
+#endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index db6ef07aec3b..b92d08e65999 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -1,18 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2018 Christoph Hellwig.
+ * Copyright (C) 2018-2020 Christoph Hellwig.
  *
  * DMA operations that map physical memory directly without using an IOMMU.
  */
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-contiguous.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/slab.h>
+#include "direct.h"
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -25,7 +26,7 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
 	if (force_dma_unencrypted(dev))
-		return __phys_to_dma(dev, phys);
+		return phys_to_dma_unencrypted(dev, phys);
 	return phys_to_dma(dev, phys);
 }
 
@@ -48,11 +49,6 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
-	if (force_dma_unencrypted(dev))
-		*phys_limit = __dma_to_phys(dev, dma_limit);
-	else
-		*phys_limit = dma_to_phys(dev, dma_limit);
-
 	/*
 	 * Optimistically try the zone that the physical address mask falls
 	 * into first.  If that returns memory that isn't actually addressable
@@ -61,6 +57,7 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
+	*phys_limit = dma_to_phys(dev, dma_limit);
 	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
 	if (*phys_limit <= DMA_BIT_MASK(32))
@@ -70,45 +67,16 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
-	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
-}
+	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
 
-/*
- * Decrypting memory is allowed to block, so if this device requires
- * unencrypted memory it must come from atomic pools.
- */
-static inline bool dma_should_alloc_from_pool(struct device *dev, gfp_t gfp,
-					      unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return false;
-	if (gfpflags_allow_blocking(gfp))
-		return false;
-	if (force_dma_unencrypted(dev))
-		return true;
-	if (!IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
-		return false;
-	if (dma_alloc_need_uncached(dev, attrs))
-		return true;
-	return false;
-}
-
-static inline bool dma_should_free_from_pool(struct device *dev,
-					     unsigned long attrs)
-{
-	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
-		return true;
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
-	    !force_dma_unencrypted(dev))
-		return false;
-	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
-		return true;
-	return false;
+	return dma_addr + size - 1 <=
+		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		gfp_t gfp, unsigned long attrs)
+		gfp_t gfp)
 {
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
@@ -116,11 +84,6 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
 
-	if (attrs & DMA_ATTR_NO_WARN)
-		gfp |= __GFP_NOWARN;
-
-	/* we always manually zero the memory once we are done: */
-	gfp &= ~__GFP_ZERO;
 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 					   &phys_limit);
 	page = dma_alloc_contiguous(dev, size, gfp);
@@ -151,7 +114,23 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	return page;
 }
 
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
+static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp)
+{
+	struct page *page;
+	u64 phys_mask;
+	void *ret;
+
+	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+					   &phys_mask);
+	page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok);
+	if (!page)
+		return NULL;
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return ret;
+}
+
+void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct page *page;
@@ -159,35 +138,44 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	int err;
 
 	size = PAGE_ALIGN(size);
-
-	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
-		u64 phys_mask;
-
-		gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-				&phys_mask);
-		page = dma_alloc_from_pool(dev, size, &ret, gfp,
-				dma_coherent_ok);
-		if (!page)
-			return NULL;
-		goto done;
-	}
-
-	page = __dma_direct_alloc_pages(dev, size, gfp, attrs);
-	if (!page)
-		return NULL;
+	if (attrs & DMA_ATTR_NO_WARN)
+		gfp |= __GFP_NOWARN;
 
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
+		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+		if (!page)
+			return NULL;
 		/* remove any dirty cache lines on the kernel alias */
 		if (!PageHighMem(page))
 			arch_dma_prep_coherent(page, size);
+		*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 		/* return the page pointer as the opaque cookie */
-		ret = page;
-		goto done;
+		return page;
 	}
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !dev_is_dma_coherent(dev))
+		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
+
+	/*
+	 * Remapping or decrypting memory may block. If either is required and
+	 * we can't block, allocate the memory from the atomic pools.
+	 */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    !gfpflags_allow_blocking(gfp) &&
+	    (force_dma_unencrypted(dev) ||
+	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
+		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
+
+	/* we always manually zero the memory once we are done */
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	if (!page)
+		return NULL;
+
 	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	     dma_alloc_need_uncached(dev, attrs)) ||
+	     !dev_is_dma_coherent(dev)) ||
 	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
 		/* remove any dirty cache lines on the kernel alias */
 		arch_dma_prep_coherent(page, size);
@@ -230,17 +218,14 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	memset(ret, 0, size);
 
 	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    dma_alloc_need_uncached(dev, attrs)) {
+	    !dev_is_dma_coherent(dev)) {
 		arch_dma_prep_coherent(page, size);
 		ret = arch_dma_set_uncached(ret, size);
 		if (IS_ERR(ret))
 			goto out_encrypt_pages;
 	}
 done:
-	if (force_dma_unencrypted(dev))
-		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
-	else
-		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 	return ret;
 
 out_encrypt_pages:
@@ -256,16 +241,11 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	return NULL;
 }
 
-void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
+void dma_direct_free(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
 	unsigned int page_order = get_order(size);
 
-	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
-	if (dma_should_free_from_pool(dev, attrs) &&
-	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
-		return;
-
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
 		/* cpu_addr is a struct page cookie, not a kernel address */
@@ -273,6 +253,18 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !dev_is_dma_coherent(dev)) {
+		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
+		return;
+	}
+
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
+		return;
+
 	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
@@ -284,25 +276,60 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
-void *dma_direct_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
+	struct page *page;
+	void *ret;
+
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
+		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
+
+	page = __dma_direct_alloc_pages(dev, size, gfp);
+	if (!page)
+		return NULL;
+	if (PageHighMem(page)) {
+		/*
+		 * Depending on the cma= arguments and per-arch setup
+		 * dma_alloc_contiguous could return highmem pages.
+		 * Without remapping there is no way to return them here,
+		 * so log an error and fail.
+		 */
+		dev_info(dev, "Rejecting highmem page from CMA.\n");
+		goto out_free_pages;
+	}
+
+	ret = page_address(page);
+	if (force_dma_unencrypted(dev)) {
+		if (set_memory_decrypted((unsigned long)ret,
+				1 << get_order(size)))
+			goto out_free_pages;
+	}
+	memset(ret, 0, size);
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return page;
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
 }
 
-void dma_direct_free(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
-	else
-		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
+	unsigned int page_order = get_order(size);
+	void *vaddr = page_address(page);
+
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    dma_free_from_pool(dev, vaddr, size))
+		return;
+
+	if (force_dma_unencrypted(dev))
+		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
+
+	dma_free_contiguous(dev, page, size);
 }
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
@@ -345,6 +372,9 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		if (unlikely(is_swiotlb_buffer(paddr)))
 			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
 					SYNC_FOR_CPU);
+
+		if (dir == DMA_FROM_DEVICE)
+			arch_dma_mark_clean(paddr, sg->length);
 	}
 
 	if (!dev_is_dma_coherent(dev))
@@ -453,13 +483,13 @@ int dma_direct_supported(struct device *dev, u64 mask)
 		return 1;
 
 	/*
-	 * This check needs to be against the actual bit mask value, so
-	 * use __phys_to_dma() here so that the SME encryption mask isn't
+	 * This check needs to be against the actual bit mask value, so use
+	 * phys_to_dma_unencrypted() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
 		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
-	return mask >= __phys_to_dma(dev, min_mask);
+	return mask >= phys_to_dma_unencrypted(dev, min_mask);
 }
 
 size_t dma_direct_max_mapping_size(struct device *dev)
@@ -476,3 +506,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
 	return !dev_is_dma_coherent(dev) ||
 		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
 }
+
+/**
+ * dma_direct_set_offset - Assign scalar offset for a single DMA range.
+ * @dev:	device pointer; needed to "own" the alloced memory.
+ * @cpu_start:  beginning of memory region covered by this offset.
+ * @dma_start:  beginning of DMA/PCI region covered by this offset.
+ * @size:	size of the region.
+ *
+ * This is for the simple case of a uniform offset which cannot
+ * be discovered by "dma-ranges".
+ *
+ * It returns -ENOMEM if out of memory, -EINVAL if a map
+ * already exists, 0 otherwise.
+ *
+ * Note: any call to this from a driver is a bug.  The mapping needs
+ * to be described by the device tree or other firmware interfaces.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+			 dma_addr_t dma_start, u64 size)
+{
+	struct bus_dma_region *map;
+	u64 offset = (u64)cpu_start - (u64)dma_start;
+
+	if (dev->dma_range_map) {
+		dev_err(dev, "attempt to add DMA range to existing map\n");
+		return -EINVAL;
+	}
+
+	if (!offset)
+		return 0;
+
+	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map[0].cpu_start = cpu_start;
+	map[0].dma_start = dma_start;
+	map[0].offset = offset;
+	map[0].size = size;
+	dev->dma_range_map = map;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_direct_set_offset);
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
new file mode 100644
index 000000000000..b98615578737
--- /dev/null
+++ b/kernel/dma/direct.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without using an IOMMU.
+ */
+#ifndef _KERNEL_DMA_DIRECT_H
+#define _KERNEL_DMA_DIRECT_H
+
+#include <linux/dma-direct.h>
+
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_can_mmap(struct device *dev);
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
+#endif /* _KERNEL_DMA_DIRECT_H */
diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
index 05607642c888..eacd4c5b10bf 100644
--- a/kernel/dma/dummy.c
+++ b/kernel/dma/dummy.c
@@ -2,7 +2,7 @@
 /*
  * Dummy DMA ops that always fail.
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
@@ -36,4 +36,3 @@ const struct dma_map_ops dma_dummy_ops = {
 	.map_sg                 = dma_dummy_map_sg,
 	.dma_supported          = dma_dummy_supported,
 };
-EXPORT_SYMBOL(dma_dummy_ops);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 0d129421e75f..51bb8fa8eb89 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -7,13 +7,14 @@
  */
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/acpi.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include "debug.h"
+#include "direct.h"
 
 /*
  * Managed DMA API
@@ -144,6 +145,10 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
 	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
@@ -179,6 +184,10 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return 0;
+
 	if (dma_map_direct(dev, ops))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
@@ -213,6 +222,9 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 
 	BUG_ON(!valid_dma_direction(dir));
 
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
 	/* Don't allow RAM to be mapped */
 	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
@@ -295,22 +307,6 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
 
-/*
- * Create scatter-list for the already allocated DMA buffer.
- */
-int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	struct page *page = virt_to_page(cpu_addr);
-	int ret;
-
-	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-	if (!ret)
-		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
-	return ret;
-}
-
 /*
  * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
  * that the intention is to allow exporting memory allocated via the
@@ -346,9 +342,7 @@ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
 {
 	if (force_dma_unencrypted(dev))
 		prot = pgprot_decrypted(prot);
-	if (dev_is_dma_coherent(dev) ||
-	    (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
-             (attrs & DMA_ATTR_NON_CONSISTENT)))
+	if (dev_is_dma_coherent(dev))
 		return prot;
 #ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE
 	if (attrs & DMA_ATTR_WRITE_COMBINE)
@@ -358,35 +352,6 @@ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
 }
 #endif /* CONFIG_MMU */
 
-/*
- * Create userspace mapping for the DMA-coherent memory.
- */
-int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs)
-{
-#ifdef CONFIG_MMU
-	unsigned long user_count = vma_pages(vma);
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long off = vma->vm_pgoff;
-	int ret = -ENXIO;
-
-	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off >= count || user_count > count - off)
-		return -ENXIO;
-
-	return remap_pfn_range(vma, vma->vm_start,
-			page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
-			user_count << PAGE_SHIFT, vma->vm_page_prot);
-#else
-	return -ENXIO;
-#endif /* CONFIG_MMU */
-}
-
 /**
  * dma_can_mmap - check if a given device supports dma_mmap_*
  * @dev: device to check
@@ -506,6 +471,86 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 }
 EXPORT_SYMBOL(dma_free_attrs);
 
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	if (WARN_ON_ONCE(!dev->coherent_dma_mask))
+		return NULL;
+	if (WARN_ON_ONCE(gfp & (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM)))
+		return NULL;
+
+	size = PAGE_ALIGN(size);
+	if (dma_alloc_direct(dev, ops))
+		page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
+	else if (ops->alloc_pages)
+		page = ops->alloc_pages(dev, size, dma_handle, dir, gfp);
+	else
+		return NULL;
+
+	debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+
+	return page;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_pages);
+
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+
+	if (dma_alloc_direct(dev, ops))
+		dma_direct_free_pages(dev, size, page, dma_handle, dir);
+	else if (ops->free_pages)
+		ops->free_pages(dev, size, page, dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_pages);
+
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *vaddr;
+
+	if (!ops || !ops->alloc_noncoherent) {
+		struct page *page;
+
+		page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+		if (!page)
+			return NULL;
+		return page_address(page);
+	}
+
+	size = PAGE_ALIGN(size);
+	vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp);
+	if (vaddr)
+		debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir,
+				   *dma_handle);
+	return vaddr;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
+
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops || !ops->free_noncoherent) {
+		dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	ops->free_noncoherent(dev, size, vaddr, dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_noncoherent);
+
 int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -563,20 +608,6 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 EXPORT_SYMBOL(dma_set_coherent_mask);
 #endif
 
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (dma_alloc_direct(dev, ops))
-		arch_dma_cache_sync(dev, vaddr, size, dir);
-	else if (ops->cache_sync)
-		ops->cache_sync(dev, vaddr, size, dir);
-}
-EXPORT_SYMBOL(dma_cache_sync);
-
 size_t dma_max_mapping_size(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
new file mode 100644
index 000000000000..910ae69cae77
--- /dev/null
+++ b/kernel/dma/ops_helpers.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helpers for DMA ops implementations.  These generally rely on the fact that
+ * the allocated memory contains normal pages in the direct kernel mapping.
+ */
+#include <linux/dma-map-ops.h>
+
+/*
+ * Create scatter-list for the already allocated DMA buffer.
+ */
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		 unsigned long attrs)
+{
+	struct page *page = virt_to_page(cpu_addr);
+	int ret;
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (!ret)
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return ret;
+}
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ */
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+#ifdef CONFIG_MMU
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
+	int ret = -ENXIO;
+
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off >= count || user_count > count - off)
+		return -ENXIO;
+
+	return remap_pfn_range(vma, vma->vm_start,
+			page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
+			user_count << PAGE_SHIFT, vma->vm_page_prot);
+#else
+	return -ENXIO;
+#endif /* CONFIG_MMU */
+}
+
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	page = dma_alloc_contiguous(dev, size, gfp);
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
+	if (!page)
+		return NULL;
+
+	*dma_handle = ops->map_page(dev, page, 0, size, dir,
+				    DMA_ATTR_SKIP_CPU_SYNC);
+	if (*dma_handle == DMA_MAPPING_ERROR) {
+		dma_free_contiguous(dev, page, size);
+		return NULL;
+	}
+
+	memset(page_address(page), 0, size);
+	return page;
+}
+
+void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops->unmap_page)
+		ops->unmap_page(dev, dma_handle, size, dir,
+				DMA_ATTR_SKIP_CPU_SYNC);
+	dma_free_contiguous(dev, page, size);
+}
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 1281c0f0442b..d4637f72239b 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -5,9 +5,8 @@
  */
 #include <linux/cma.h>
 #include <linux/debugfs.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/init.h>
 #include <linux/genalloc.h>
 #include <linux/set_memory.h>
@@ -115,7 +114,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 #endif
 	/*
 	 * Memory in the atomic DMA pools must be unencrypted, the pools do not
-	 * shrink so no re-encryption occurs in dma_direct_free_pages().
+	 * shrink so no re-encryption occurs in dma_direct_free().
 	 */
 	ret = set_memory_decrypted((unsigned long)page_to_virt(page),
 				   1 << order);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 465a567678d9..b4eea0abc3f0 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -22,7 +22,7 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -668,13 +668,13 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 			      swiotlb_force);
 
 	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			__phys_to_dma(dev, io_tlb_start),
+			phys_to_dma_unencrypted(dev, io_tlb_start),
 			paddr, size, size, dir, attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
 	/* Ensure that the address returned is DMA'ble */
-	dma_addr = __phys_to_dma(dev, swiotlb_addr);
+	dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
 		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
index ebe128833af7..59d32317dd57 100644
--- a/kernel/dma/virt.c
+++ b/kernel/dma/virt.c
@@ -4,7 +4,7 @@
  */
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 static void *dma_virt_alloc(struct device *dev, size_t size,
@@ -55,5 +55,7 @@ const struct dma_map_ops dma_virt_ops = {
 	.free			= dma_virt_free,
 	.map_page		= dma_virt_map_page,
 	.map_sg			= dma_virt_map_sg,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(dma_virt_ops);
diff --git a/mm/Kconfig b/mm/Kconfig
index 8c60c49a123b..e72e61c1d62e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -516,13 +516,14 @@ config CMA_DEBUGFS
 config CMA_AREAS
 	int "Maximum count of the CMA areas"
 	depends on CMA
+	default 19 if NUMA
 	default 7
 	help
 	  CMA allows to create CMA areas for particular purpose, mainly,
 	  used as device private area. This parameter sets the maximum
 	  number of CMA area in the system.
 
-	  If unsure, leave the default value "7".
+	  If unsure, leave the default value "7" in UMA and "19" in NUMA.
 
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
diff --git a/mm/cma.h b/mm/cma.h
index 20f6e24bc477..42ae082cb067 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -4,8 +4,6 @@
 
 #include <linux/debugfs.h>
 
-#define CMA_MAX_NAME 64
-
 struct cma {
 	unsigned long   base_pfn;
 	unsigned long   count;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ddbd3b355361..fe76f8fd5a73 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5706,12 +5706,12 @@ void __init hugetlb_cma_reserve(int order)
 	reserved = 0;
 	for_each_node_state(nid, N_ONLINE) {
 		int res;
-		char name[20];
+		char name[CMA_MAX_NAME];
 
 		size = min(per_node, hugetlb_cma_size - reserved);
 		size = round_up(size, PAGE_SIZE << order);
 
-		snprintf(name, 20, "hugetlb%d", nid);
+		snprintf(name, sizeof(name), "hugetlb%d", nid);
 		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
 						 0, false, name,
 						 &hugetlb_cma[nid], nid);
diff --git a/mm/memory.c b/mm/memory.c
index f482af8bc828..2afb01ea1307 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -65,7 +65,6 @@
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
-#include <linux/dma-debug.h>
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
diff --git a/sound/mips/hal2.c b/sound/mips/hal2.c
index ec84bc4c3a6e..9ac9b58d7c8c 100644
--- a/sound/mips/hal2.c
+++ b/sound/mips/hal2.c
@@ -441,7 +441,8 @@ static inline void hal2_stop_adc(struct snd_hal2 *hal2)
 	hal2->adc.pbus.pbus->pbdma_ctrl = HPC3_PDMACTRL_LD;
 }
 
-static int hal2_alloc_dmabuf(struct snd_hal2 *hal2, struct hal2_codec *codec)
+static int hal2_alloc_dmabuf(struct snd_hal2 *hal2, struct hal2_codec *codec,
+		enum dma_data_direction buffer_dir)
 {
 	struct device *dev = hal2->card->dev;
 	struct hal2_desc *desc;
@@ -449,15 +450,15 @@ static int hal2_alloc_dmabuf(struct snd_hal2 *hal2, struct hal2_codec *codec)
 	int count = H2_BUF_SIZE / H2_BLOCK_SIZE;
 	int i;
 
-	codec->buffer = dma_alloc_attrs(dev, H2_BUF_SIZE, &buffer_dma,
-					GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
+	codec->buffer = dma_alloc_noncoherent(dev, H2_BUF_SIZE, &buffer_dma,
+					buffer_dir, GFP_KERNEL);
 	if (!codec->buffer)
 		return -ENOMEM;
-	desc = dma_alloc_attrs(dev, count * sizeof(struct hal2_desc),
-			       &desc_dma, GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
+	desc = dma_alloc_noncoherent(dev, count * sizeof(struct hal2_desc),
+			&desc_dma, DMA_BIDIRECTIONAL, GFP_KERNEL);
 	if (!desc) {
-		dma_free_attrs(dev, H2_BUF_SIZE, codec->buffer, buffer_dma,
-			       DMA_ATTR_NON_CONSISTENT);
+		dma_free_noncoherent(dev, H2_BUF_SIZE, codec->buffer, buffer_dma,
+				buffer_dir);
 		return -ENOMEM;
 	}
 	codec->buffer_dma = buffer_dma;
@@ -470,20 +471,22 @@ static int hal2_alloc_dmabuf(struct snd_hal2 *hal2, struct hal2_codec *codec)
 		      desc_dma : desc_dma + (i + 1) * sizeof(struct hal2_desc);
 		desc++;
 	}
-	dma_cache_sync(dev, codec->desc, count * sizeof(struct hal2_desc),
-		       DMA_TO_DEVICE);
+	dma_sync_single_for_device(dev, codec->desc_dma,
+				   count * sizeof(struct hal2_desc),
+				   DMA_BIDIRECTIONAL);
 	codec->desc_count = count;
 	return 0;
 }
 
-static void hal2_free_dmabuf(struct snd_hal2 *hal2, struct hal2_codec *codec)
+static void hal2_free_dmabuf(struct snd_hal2 *hal2, struct hal2_codec *codec,
+		enum dma_data_direction buffer_dir)
 {
 	struct device *dev = hal2->card->dev;
 
-	dma_free_attrs(dev, codec->desc_count * sizeof(struct hal2_desc),
-		       codec->desc, codec->desc_dma, DMA_ATTR_NON_CONSISTENT);
-	dma_free_attrs(dev, H2_BUF_SIZE, codec->buffer, codec->buffer_dma,
-		       DMA_ATTR_NON_CONSISTENT);
+	dma_free_noncoherent(dev, codec->desc_count * sizeof(struct hal2_desc),
+		       codec->desc, codec->desc_dma, DMA_BIDIRECTIONAL);
+	dma_free_noncoherent(dev, H2_BUF_SIZE, codec->buffer, codec->buffer_dma,
+			buffer_dir);
 }
 
 static const struct snd_pcm_hardware hal2_pcm_hw = {
@@ -509,21 +512,16 @@ static int hal2_playback_open(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_hal2 *hal2 = snd_pcm_substream_chip(substream);
-	int err;
 
 	runtime->hw = hal2_pcm_hw;
-
-	err = hal2_alloc_dmabuf(hal2, &hal2->dac);
-	if (err)
-		return err;
-	return 0;
+	return hal2_alloc_dmabuf(hal2, &hal2->dac, DMA_TO_DEVICE);
 }
 
 static int hal2_playback_close(struct snd_pcm_substream *substream)
 {
 	struct snd_hal2 *hal2 = snd_pcm_substream_chip(substream);
 
-	hal2_free_dmabuf(hal2, &hal2->dac);
+	hal2_free_dmabuf(hal2, &hal2->dac, DMA_TO_DEVICE);
 	return 0;
 }
 
@@ -579,7 +577,9 @@ static void hal2_playback_transfer(struct snd_pcm_substream *substream,
 	unsigned char *buf = hal2->dac.buffer + rec->hw_data;
 
 	memcpy(buf, substream->runtime->dma_area + rec->sw_data, bytes);
-	dma_cache_sync(hal2->card->dev, buf, bytes, DMA_TO_DEVICE);
+	dma_sync_single_for_device(hal2->card->dev,
+			hal2->dac.buffer_dma + rec->hw_data, bytes,
+			DMA_TO_DEVICE);
 
 }
 
@@ -597,22 +597,16 @@ static int hal2_capture_open(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_hal2 *hal2 = snd_pcm_substream_chip(substream);
-	struct hal2_codec *adc = &hal2->adc;
-	int err;
 
 	runtime->hw = hal2_pcm_hw;
-
-	err = hal2_alloc_dmabuf(hal2, adc);
-	if (err)
-		return err;
-	return 0;
+	return hal2_alloc_dmabuf(hal2, &hal2->adc, DMA_FROM_DEVICE);
 }
 
 static int hal2_capture_close(struct snd_pcm_substream *substream)
 {
 	struct snd_hal2 *hal2 = snd_pcm_substream_chip(substream);
 
-	hal2_free_dmabuf(hal2, &hal2->adc);
+	hal2_free_dmabuf(hal2, &hal2->adc, DMA_FROM_DEVICE);
 	return 0;
 }
 
@@ -667,7 +661,9 @@ static void hal2_capture_transfer(struct snd_pcm_substream *substream,
 	struct snd_hal2 *hal2 = snd_pcm_substream_chip(substream);
 	unsigned char *buf = hal2->adc.buffer + rec->hw_data;
 
-	dma_cache_sync(hal2->card->dev, buf, bytes, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(hal2->card->dev,
+			hal2->adc.buffer_dma + rec->hw_data, bytes,
+			DMA_FROM_DEVICE);
 	memcpy(substream->runtime->dma_area + rec->sw_data, buf, bytes);
 }