Merge tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - rework the non-coherent DMA allocator

 - move private definitions out of <linux/dma-mapping.h>

 - lower CMA_ALIGNMENT (Paul Cercueil)

 - remove the omap1 dma address translation in favor of the common code

 - make dma-direct aware of multiple dma offset ranges (Jim Quinlan)

 - support per-node DMA CMA areas (Barry Song)

 - increase the default seg boundary limit (Nicolin Chen)

 - misc fixes (Robin Murphy, Thomas Tai, Xu Wang)

 - various cleanups

* tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping: (63 commits)
  ARM/ixp4xx: add a missing include of dma-map-ops.h
  dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling
  dma-direct: factor out a dma_direct_alloc_from_pool helper
  dma-direct check for highmem pages in dma_direct_alloc_pages
  dma-mapping: merge <linux/dma-noncoherent.h> into <linux/dma-map-ops.h>
  dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma
  dma-mapping: move dma-debug.h to kernel/dma/
  dma-mapping: remove <asm/dma-contiguous.h>
  dma-mapping: merge <linux/dma-contiguous.h> into <linux/dma-map-ops.h>
  dma-contiguous: remove dma_contiguous_set_default
  dma-contiguous: remove dev_set_cma_area
  dma-contiguous: remove dma_declare_contiguous
  dma-mapping: split <linux/dma-mapping.h>
  cma: decrease CMA_ALIGNMENT lower limit to 2
  firewire-ohci: use dma_alloc_pages
  dma-iommu: implement ->alloc_noncoherent
  dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods
  dma-mapping: add a new dma_alloc_pages API
  dma-mapping: remove dma_cache_sync
  53c700: convert to dma_alloc_noncoherent
  ...

10 files changed, 468 insertions, 766 deletions

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-debug.h b/include/linux/dma-debug.h
deleted file mode 100644
index 7b3b04ba60f3..000000000000
--- a/include/linux/dma-debug.h
+++ /dev/null
@@ -1,160 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2008 Advanced Micro Devices, Inc.
- *
- * 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;
-
-#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);
-
-extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, int mapped_ents, int direction);
-
-extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-			       int nelems, int dir);
-
-extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
-				     dma_addr_t dma_addr, void *virt);
-
-extern void debug_dma_free_coherent(struct device *dev, size_t size,
-				    void *virt, dma_addr_t addr);
-
-extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-				   size_t size, int direction,
-				   dma_addr_t dma_addr);
-
-extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-				     size_t size, int direction);
-
-extern void debug_dma_sync_single_for_cpu(struct device *dev,
-					  dma_addr_t dma_handle, size_t size,
-					  int direction);
-
-extern void debug_dma_sync_single_for_device(struct device *dev,
-					     dma_addr_t dma_handle,
-					     size_t size, int direction);
-
-extern void debug_dma_sync_sg_for_cpu(struct device *dev,
-				      struct scatterlist *sg,
-				      int nelems, int direction);
-
-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)
-{
-}
-
-static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
-				    int nents, int mapped_ents, int direction)
-{
-}
-
-static inline void debug_dma_unmap_sg(struct device *dev,
-				      struct scatterlist *sglist,
-				      int nelems, int dir)
-{
-}
-
-static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
-					    dma_addr_t dma_addr, void *virt)
-{
-}
-
-static inline void debug_dma_free_coherent(struct device *dev, size_t size,
-					   void *virt, dma_addr_t addr)
-{
-}
-
-static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-					  size_t size, int direction,
-					  dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_unmap_resource(struct device *dev,
-					    dma_addr_t dma_addr, size_t size,
-					    int direction)
-{
-}
-
-static inline void debug_dma_sync_single_for_cpu(struct device *dev,
-						 dma_addr_t dma_handle,
-						 size_t size, int direction)
-{
-}
-
-static inline void debug_dma_sync_single_for_device(struct device *dev,
-						    dma_addr_t dma_handle,
-						    size_t size, int direction)
-{
-}
-
-static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
-					     struct scatterlist *sg,
-					     int nelems, int direction)
-{
-}
-
-static inline void debug_dma_sync_sg_for_device(struct device *dev,
-						struct scatterlist *sg,
-						int nelems, int direction)
-{
-}
-
-static inline void debug_dma_dump_mappings(struct device *dev)
-{
-}
-
-#endif /* CONFIG_DMA_API_DEBUG */
-
-#endif /* __DMA_DEBUG_H */
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
@@ -7,64 +7,102 @@
 #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)
+/*
+ * 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;
+};
+
+static inline dma_addr_t translate_phys_to_dma(struct device *dev,
+		phys_addr_t paddr)
 {
-	dma_addr_t dev_addr = (dma_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;
 
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	/* 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;
 }
-#endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
-#ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED
-bool force_dma_unencrypted(struct device *dev);
+#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 bool force_dma_unencrypted(struct device *dev)
+static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
+		phys_addr_t paddr)
 {
-	return false;
+	if (dev->dma_range_map)
+		return translate_phys_to_dma(dev, paddr);
+	return paddr;
 }
-#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.
+ * 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(dev, paddr));
+	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
 }
 
-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 dma_addr)
 {
-	return __sme_clr(__dma_to_phys(dev, daddr));
+	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 */
+
+#ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED
+bool force_dma_unencrypted(struct device *dev);
+#else
+static inline bool force_dma_unencrypted(struct device *dev)
+{
+	return false;
 }
+#endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 
 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>
@@ -28,11 +27,6 @@
  */
 #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)
-{
-	return NULL;
-}
-
-static inline int dma_release_from_global_coherent(int order, void *vaddr)
+static inline void debug_dma_mapping_error(struct device *dev,
+		dma_addr_t dma_addr)
 {
-	return 0;
 }
-
-static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
-						void *cpu_addr, size_t size,
-						int *ret)
+static inline void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len)
 {
-	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) \