dma-mapping updates for 5.10

- 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
 -----BEGIN PGP SIGNATURE-----
 
 iQI/BAABCgApFiEEgdbnc3r/njty3Iq9D55TZVIEUYMFAl+IiPwLHGhjaEBsc3Qu
 ZGUACgkQD55TZVIEUYPKEQ//TM8vxjucnRl/pklpMin49dJorwiVvROLhQqLmdxw
 286ZKpVzYYAPc7LnNqwIBugnFZiXuHu8xPKQkIiOa2OtNDTwhKNoBxOAmOJaV6DD
 8JfEtZYeX5mKJ/Nqd2iSkIqOvCwZ9Wzii+aytJ2U88wezQr1fnyF4X49MegETEey
 FHWreSaRWZKa0MMRu9AQ0QxmoNTHAQUNaPc0PeqEtPULybfkGOGw4/ghSB7WcKrA
 gtKTuooNOSpVEHkTas2TMpcBp6lxtOjFqKzVN0ml+/nqq5NeTSDx91VOCX/6Cj76
 mXIg+s7fbACTk/BmkkwAkd0QEw4fo4tyD6Bep/5QNhvEoAriTuSRbhvLdOwFz0EF
 vhkF0Rer6umdhSK7nPd7SBqn8kAnP4vBbdmB68+nc3lmkqysLyE4VkgkdH/IYYQI
 6TJ0oilXWFmU6DT5Rm4FBqCvfcEfU2dUIHJr5wZHqrF2kLzoZ+mpg42fADoG4GuI
 D/oOsz7soeaRe3eYfWybC0omGR6YYPozZJ9lsfftcElmwSsFrmPsbO1DM5IBkj1B
 gItmEbOB9ZK3RhIK55T/3u1UWY3Uc/RVr+kchWvADGrWnRQnW0kxYIqDgiOytLFi
 JZNH8uHpJIwzoJAv6XXSPyEUBwXTG+zK37Ce769HGbUEaUrE71MxBbQAQsK8mDpg
 7fM=
 =Bkf/
 -----END PGP SIGNATURE-----

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
  ...

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

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
+These APIs allow to allocate pages in the kernel direct mapping that are
-majority of cases, since they cater for unlikely corner cases that
+guaranteed to be DMA addressable.  This means that unlike dma_alloc_coherent,
-don't belong in usual drivers.
+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
+If you don't understand how cache line coherency works between a processor and
-processor and an I/O device, you should not be using this part of the
+an I/O device, you should not be using this part of the API.
-API at all.
 
 ::
 
 	void *
-	dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+	dma_alloc_noncoherent(struct device *dev, size_t size,
-			gfp_t flag, unsigned long attrs)
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp)
 
-Identical to dma_alloc_coherent() except that when the
+This routine allocates a region of <size> bytes of consistent memory.  It
-DMA_ATTR_NON_CONSISTENT flags is passed in the attrs argument, the
+returns a pointer to the allocated region (in the processor's virtual address
-platform will choose to return either consistent or non-consistent memory
+space) or NULL if the allocation failed.  The returned memory may or may not
-as it sees fit.  By using this API, you are guaranteeing to the platform
+be in the kernels direct mapping.  Drivers must not call virt_to_page on
-that you have all the correct and necessary sync points for this memory
+the returned memory region.
-in the driver should it choose to return non-consistent memory.
 
-Note: where the platform can return consistent memory, it will
+It also returns a <dma_handle> which may be cast to an unsigned integer the
-guarantee that the sync points become nops.
+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
+The dir parameter specified if data is read and/or written by the device,
-only use this API if you positively know your driver will be
+see dma_map_single() for details.
-required to work on one of the rare (usually non-PCI) architectures
+
-that simply cannot make consistent memory.
+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_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
-		       dma_addr_t dma_handle, unsigned long attrs)
+			dma_addr_t dma_handle, enum dma_data_direction dir)
 
-Free memory allocated by the dma_alloc_attrs().  All common
+Free a region of memory previously allocated using dma_alloc_noncoherent().
-parameters must be identical to those otherwise passed to dma_free_coherent,
+dev, size and dma_handle and dir must all be the same as those passed into
-and the attrs argument must be identical to the attrs passed to
+dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
-dma_alloc_attrs().
+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
 -------------------------------------------

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
 --------------------------
 

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

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_nr_pages(dev, PAGE_SHIFT);
-		boundary_size = dma_get_seg_boundary(dev) + 1;
-		boundary_size >>= PAGE_SHIFT;
-	} else {
-		boundary_size = 1UL << (32 - 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);

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>
 

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>

arch/arm/include/asm/dma-contiguous.h

@@ -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

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;

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 {

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

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);
+	ret = dma_contiguous_reserve_area(rproc_size, rproc_base, 0, &cma,
-	if (ret)
+			true);
-		pr_err("%s: dma_declare_contiguous failed %d\n", __func__, ret);
+	if (ret) {
-	else
+		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)

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>

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>

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>

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>

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;
+		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
-		dev_err(dev, "set dma_pfn_offset%08lx\n",
+						KEYSTONE_LOW_PHYS_START,
-			dev->dma_pfn_offset);
+						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) {
+#ifdef CONFIG_ARM_LPAE
-		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
-						   KEYSTONE_LOW_PHYS_START);
 		bus_register_notifier(&platform_bus_type, &platform_nb);
-	}
+#endif
 	keystone_pm_runtime_init();
 }
 

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>

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

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)

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>

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,

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-map-ops.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.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,

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>

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>

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>

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-map-ops.h>
-#include <linux/dma-contiguous.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

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>

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>

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-map-ops.h>
-#include <linux/dma-contiguous.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>

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>

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

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 = dma_get_seg_boundary_nr_pages(dev, iovp_shift);
-	boundary_size = ALIGN(boundary_size, 1ULL << iovp_shift) >> 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

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);
-}

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,
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
-		enum dma_data_direction dir)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 

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>

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>

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>
 

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>

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

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;
 

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))

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);
+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);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */

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 */

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-map-ops.h>
-#include <linux/dma-noncoherent.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 (attrs & DMA_ATTR_NO_WARN)
-	if (!ret)
+		gfp |= __GFP_NOWARN;
-		return NULL;
 
+	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) {
+	if (*dma_handle == DMA_MAPPING_ERROR)
-		dma_direct_free_pages(dev, size, ret, *dma_handle, attrs);
+		goto out_free_pages;
-		return NULL;
+	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);

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>

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;
 }

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;

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 */

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-map-ops.h>
-#include <linux/dma-contiguous.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;
-
-		if (PageHighMem(page)) {
 		void *addr;
 
+		if (PageHighMem(page)) {
 			if (offset + len > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
+		}
 
 		addr = kmap_atomic(page);
-			dma_sync_virt(addr + offset, len, dir);
+		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);
-		} 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)

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);
 }

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);
 }

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;
 

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>

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>

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

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>

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);
-}

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;
 }

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>

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>

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,
 };

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 */

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>

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,
 };
 
 /**

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>

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,
 };
 
 /**

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>

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);

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>

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>

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>
 

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>

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>

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>

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>

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)

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>
 

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);

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,
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
-				  IO_PAGE_SIZE) >> 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;

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>

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,
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))

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>
 

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>
 

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;

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,
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
-			      PAGE_SIZE) >> 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)

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>

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>
 

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);

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>
 

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-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/dma-direct.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>

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>

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);
+	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
-	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
+
+	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,

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>
 

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)

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>

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>

drivers/firewire/ohci.c

@@ -674,16 +674,15 @@ 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++)
+	for (i = 0; i < AR_BUFFERS; i++) {
-		if (ctx->pages[i]) {
+		if (ctx->pages[i])
-			dma_unmap_page(ctx->ohci->card.device,
+			dma_free_pages(dev, PAGE_SIZE, ctx->pages[i],
-				       ar_buffer_bus(ctx, i),
+				       ar_buffer_bus(ctx, i), DMA_FROM_DEVICE);
-				       PAGE_SIZE, DMA_FROM_DEVICE);
-			__free_page(ctx->pages[i]);
 	}
 }
 
@@ -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++)

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>
 

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)