Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping

Pull DMA mapping updates from Christoph Hellwig:
"A huge update this time, but a lot of that is just consolidating or
removing code:

- provide a common DMA_MAPPING_ERROR definition and avoid indirect
calls for dma_map_* error checking

- use direct calls for the DMA direct mapping case, avoiding huge
retpoline overhead for high performance workloads

- merge the swiotlb dma_map_ops into dma-direct

- provide a generic remapping DMA consistent allocator for
architectures that have devices that perform DMA that is not cache
coherent. Based on the existing arm64 implementation and also used
for csky now.

- improve the dma-debug infrastructure, including dynamic allocation
of entries (Robin Murphy)

- default to providing chaining scatterlist everywhere, with opt-outs
for the few architectures (alpha, parisc, most arm32 variants) that
can't cope with it

- misc sparc32 dma-related cleanups

- remove the dma_mark_clean arch hook used by swiotlb on ia64 and
replace it with the generic noncoherent infrastructure

- fix the return type of dma_set_max_seg_size (Niklas Söderlund)

- move the dummy dma ops for not DMA capable devices from arm64 to
common code (Robin Murphy)

- ensure dma_alloc_coherent returns zeroed memory to avoid kernel
data leaks through userspace. We already did this for most common
architectures, but this ensures we do it everywhere.
dma_zalloc_coherent has been deprecated and can hopefully be
removed after -rc1 with a coccinelle script"

* tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits)
dma-mapping: fix inverted logic in dma_supported
dma-mapping: deprecate dma_zalloc_coherent
dma-mapping: zero memory returned from dma_alloc_*
sparc/iommu: fix ->map_sg return value
sparc/io-unit: fix ->map_sg return value
arm64: default to the direct mapping in get_arch_dma_ops
PCI: Remove unused attr variable in pci_dma_configure
ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled
dma-mapping: bypass indirect calls for dma-direct
vmd: use the proper dma_* APIs instead of direct methods calls
dma-direct: merge swiotlb_dma_ops into the dma_direct code
dma-direct: use dma_direct_map_page to implement dma_direct_map_sg
dma-direct: improve addressability error reporting
swiotlb: remove dma_mark_clean
swiotlb: remove SWIOTLB_MAP_ERROR
ACPI / scan: Refactor _CCA enforcement
dma-mapping: factor out dummy DMA ops
dma-mapping: always build the direct mapping code
dma-mapping: move dma_cache_sync out of line
dma-mapping: move various slow path functions out of line
...

Documentation/DMA-API.txt

···
 
 ::
 
-	void *
-	dma_zalloc_coherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t flag)
-
-Wraps dma_alloc_coherent() and also zeroes the returned memory if the
-allocation attempt succeeded.
-
-::
-
 	void
 	dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 			  dma_addr_t dma_handle)
···
 dma-api/min_free_entries	This read-only file can be read to get the
 				minimum number of free dma_debug_entries the
 				allocator has ever seen. If this value goes
-				down to zero the code will disable itself
-				because it is not longer reliable.
+				down to zero the code will attempt to increase
+				nr_total_entries to compensate.
 
 dma-api/num_free_entries	The current number of free dma_debug_entries
 				in the allocator.
+
+dma-api/nr_total_entries	The total number of dma_debug_entries in the
+				allocator, both free and used.
 
 dma-api/driver-filter		You can write a name of a driver into this file
 				to limit the debug output to requests from that
···
 driver afterwards. This filter can be disabled or changed later using debugfs.
 
 When the code disables itself at runtime this is most likely because it ran
-out of dma_debug_entries. These entries are preallocated at boot. The number
-of preallocated entries is defined per architecture. If it is too low for you
-boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
-architectural default.
+out of dma_debug_entries and was unable to allocate more on-demand. 65536
+entries are preallocated at boot - if this is too low for you boot with
+'dma_debug_entries=<your_desired_number>' to overwrite the default. Note
+that the code allocates entries in batches, so the exact number of
+preallocated entries may be greater than the actual number requested. The
+code will print to the kernel log each time it has dynamically allocated
+as many entries as were initially preallocated. This is to indicate that a
+larger preallocation size may be appropriate, or if it happens continually
+that a driver may be leaking mappings.
 
 ::
 

Documentation/features/io/sg-chain/arch-support.txt

···
-#
-# Feature name:          sg-chain
-#         Kconfig:       ARCH_HAS_SG_CHAIN
-#         description:   arch supports chained scatter-gather lists
-#
-    -----------------------
-    |         arch |status|
-    -----------------------
-    |       alpha: | TODO |
-    |         arc: |  ok  |
-    |         arm: |  ok  |
-    |       arm64: |  ok  |
-    |         c6x: | TODO |
-    |       h8300: | TODO |
-    |     hexagon: | TODO |
-    |        ia64: |  ok  |
-    |        m68k: | TODO |
-    |  microblaze: | TODO |
-    |        mips: | TODO |
-    |       nds32: | TODO |
-    |       nios2: | TODO |
-    |    openrisc: | TODO |
-    |      parisc: | TODO |
-    |     powerpc: |  ok  |
-    |       riscv: | TODO |
-    |        s390: |  ok  |
-    |          sh: | TODO |
-    |       sparc: |  ok  |
-    |          um: | TODO |
-    |   unicore32: | TODO |
-    |         x86: |  ok  |
-    |      xtensa: | TODO |
-    -----------------------

Documentation/x86/x86_64/boot-options.txt

···
       mapping with memory protection, etc.
       Kernel boot message: "PCI-DMA: Using Calgary IOMMU"
 
- iommu=[<size>][,noagp][,off][,force][,noforce][,leak[=<nr_of_leak_pages>]
+ iommu=[<size>][,noagp][,off][,force][,noforce]
 	[,memaper[=<order>]][,merge][,fullflush][,nomerge]
 	[,noaperture][,calgary]
 
···
     allowed            Overwrite iommu off workarounds for specific chipsets.
     fullflush          Flush IOMMU on each allocation (default).
     nofullflush        Don't use IOMMU fullflush.
-    leak               Turn on simple iommu leak tracing (only when
-                       CONFIG_IOMMU_LEAK is on). Default number of leak pages
-                       is 20.
     memaper[=<order>]  Allocate an own aperture over RAM with size 32MB<<order.
                        (default: order=1, i.e. 64MB)
     merge              Do scatter-gather (SG) merging. Implies "force"

arch/alpha/Kconfig

···
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_NO_PREEMPT
+	select ARCH_NO_SG_CHAIN
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_AOUT
 	select HAVE_IDE
···
 config ALPHA_JENSEN
 	bool "Jensen"
 	depends on BROKEN
-	select DMA_DIRECT_OPS
 	help
 	  DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one
 	  of the first-generation Alpha systems. A number of these systems

arch/alpha/include/asm/dma-mapping.h

···
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 #ifdef CONFIG_ALPHA_JENSEN
-	return &dma_direct_ops;
+	return NULL;
 #else
 	return &alpha_pci_ops;
 #endif

arch/alpha/kernel/pci_iommu.c

···
 	   use direct_map above, it now must be considered an error. */
 	if (! alpha_mv.mv_pci_tbi) {
 		printk_once(KERN_WARNING "pci_map_single: no HW sg\n");
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 
 	arena = hose->sg_pci;
···
 	if (dma_ofs < 0) {
 		printk(KERN_WARNING "pci_map_single failed: "
 		       "could not allocate dma page tables\n");
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 
 	paddr &= PAGE_MASK;
···
 	gfp &= ~GFP_DMA;
 
 try_again:
-	cpu_addr = (void *)__get_free_pages(gfp, order);
+	cpu_addr = (void *)__get_free_pages(gfp | __GFP_ZERO, order);
 	if (! cpu_addr) {
 		printk(KERN_INFO "pci_alloc_consistent: "
 		       "get_free_pages failed from %pf\n",
···
 	memset(cpu_addr, 0, size);
 
 	*dma_addrp = pci_map_single_1(pdev, cpu_addr, size, 0);
-	if (*dma_addrp == 0) {
+	if (*dma_addrp == DMA_MAPPING_ERROR) {
 		free_pages((unsigned long)cpu_addr, order);
 		if (alpha_mv.mv_pci_tbi || (gfp & GFP_DMA))
 			return NULL;
···
 		sg->dma_address
 		  = pci_map_single_1(pdev, SG_ENT_VIRT_ADDRESS(sg),
 				     sg->length, dac_allowed);
-		return sg->dma_address != 0;
+		return sg->dma_address != DMA_MAPPING_ERROR;
 	}
 
 	start = sg;
···
 	return 0;
 }
 
-static int alpha_pci_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == 0;
-}
-
 const struct dma_map_ops alpha_pci_ops = {
 	.alloc			= alpha_pci_alloc_coherent,
 	.free			= alpha_pci_free_coherent,
···
 	.unmap_page		= alpha_pci_unmap_page,
 	.map_sg			= alpha_pci_map_sg,
 	.unmap_sg		= alpha_pci_unmap_sg,
-	.mapping_error		= alpha_pci_mapping_error,
 	.dma_supported		= alpha_pci_supported,
 };
 EXPORT_SYMBOL(alpha_pci_ops);

arch/arc/Kconfig

···
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_FIND_FIRST_BIT

arch/arc/mm/cache.c

···
 	/*
 	 * In case of IOC (say IOC+SLC case), pointers above could still be set
 	 * but end up not being relevant as the first function in chain is not
-	 * called at all for @dma_direct_ops
+	 * called at all for devices using coherent DMA.
 	 *     arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*()
 	 */
 }

arch/arc/mm/dma.c

···
 	 */
 	BUG_ON(gfp & __GFP_HIGHMEM);
 
-	page = alloc_pages(gfp, order);
+	page = alloc_pages(gfp | __GFP_ZERO, order);
 	if (!page)
 		return NULL;
 

arch/arm/Kconfig

···
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_NO_SG_CHAIN if !ARM_HAS_SG_CHAIN
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
···
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select DMA_DIRECT_OPS if !MMU
+	select DMA_REMAP if MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR
···
 	  <http://www.arm.linux.org.uk/>.
 
 config ARM_HAS_SG_CHAIN
-	select ARCH_HAS_SG_CHAIN
 	bool
 
 config ARM_DMA_USE_IOMMU

arch/arm/common/dmabounce.c

···
 	if (buf == NULL) {
 		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
 		       __func__, ptr);
-		return ARM_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
···
 
 	ret = needs_bounce(dev, dma_addr, size);
 	if (ret < 0)
-		return ARM_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	if (ret == 0) {
 		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
···
 
 	if (PageHighMem(page)) {
 		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
-		return ARM_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	return map_single(dev, page_address(page) + offset, size, dir, attrs);
···
 	return arm_dma_ops.dma_supported(dev, dma_mask);
 }
 
-static int dmabounce_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return arm_dma_ops.mapping_error(dev, dma_addr);
-}
-
 static const struct dma_map_ops dmabounce_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
···
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
 	.dma_supported		= dmabounce_dma_supported,
-	.mapping_error		= dmabounce_mapping_error,
 };
 
 static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,

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

···
 #include <linux/dma-debug.h>
 #include <linux/kref.h>
 
-#define ARM_MAPPING_ERROR		(~(dma_addr_t)0x0)
-
 struct dma_iommu_mapping {
 	/* iommu specific data */
 	struct iommu_domain	*domain;

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

···
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops;
+	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL;
 }
 
 #ifdef __arch_page_to_dma

arch/arm/mm/dma-mapping-nommu.c

···
 #include "dma.h"
 
 /*
- *  dma_direct_ops is used if
+ *  The generic direct mapping code is used if
  *   - MMU/MPU is off
  *   - cpu is v7m w/o cache support
  *   - device is coherent
···
 };
 EXPORT_SYMBOL(arm_nommu_dma_ops);
 
-static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
-{
-	return coherent ? &dma_direct_ops : &arm_nommu_dma_ops;
-}
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	const struct dma_map_ops *dma_ops;
-
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
 		 * Cache support for v7m is optional, so can be treated as
···
 		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
 	}
 
-	dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
-
-	set_dma_ops(dev, dma_ops);
+	if (!dev->archdata.dma_coherent)
+		set_dma_ops(dev, &arm_nommu_dma_ops);
 }

arch/arm/mm/dma-mapping.c

···
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
-static int arm_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == ARM_MAPPING_ERROR;
-}
-
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
···
 	.sync_single_for_device	= arm_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_dma_ops);
···
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
···
 	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 	allowblock = gfpflags_allow_blocking(gfp);
 	cma = allowblock ? dev_get_cma_area(dev) : false;
 
···
 	if (i == mapping->nr_bitmaps) {
 		if (extend_iommu_mapping(mapping)) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return ARM_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
···
 
 		if (start > mapping->bits) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return ARM_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		bitmap_set(mapping->bitmaps[i], start, count);
···
 	int i;
 
 	dma_addr = __alloc_iova(mapping, size);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	iova = dma_addr;
···
 fail:
 	iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
 	__free_iova(mapping, dma_addr, size);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
···
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, &page, size, attrs);
-	if (*handle == ARM_MAPPING_ERROR)
+	if (*handle == DMA_MAPPING_ERROR)
 		goto err_mapping;
 
 	return addr;
···
 	struct page **pages;
 	void *addr = NULL;
 
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
···
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, pages, size, attrs);
-	if (*handle == ARM_MAPPING_ERROR)
+	if (*handle == DMA_MAPPING_ERROR)
 		goto err_buffer;
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
···
 	int prot;
 
 	size = PAGE_ALIGN(size);
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 
 	iova_base = iova = __alloc_iova(mapping, size);
-	if (iova == ARM_MAPPING_ERROR)
+	if (iova == DMA_MAPPING_ERROR)
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
···
 	for (i = 1; i < nents; i++) {
 		s = sg_next(s);
 
-		s->dma_address = ARM_MAPPING_ERROR;
+		s->dma_address = DMA_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
···
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs);
···
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /**
···
 	size_t len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
···
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /**
···
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
 
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 
···
 	.map_resource	= arm_iommu_map_resource,
 	.unmap_resource	= arm_iommu_unmap_resource,
 
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 

arch/arm64/Kconfig

···
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
···
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select CRC32
 	select DCACHE_WORD_ACCESS
-	select DMA_DIRECT_OPS
+	select DMA_DIRECT_REMAP
 	select EDAC_SUPPORT
 	select FRAME_POINTER
 	select GENERIC_ALLOCATOR

arch/arm64/include/asm/dma-mapping.h

···
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-extern const struct dma_map_ops dummy_dma_ops;
-
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	/*
-	 * We expect no ISA devices, and all other DMA masters are expected to
-	 * have someone call arch_setup_dma_ops at device creation time.
-	 */
-	return &dummy_dma_ops;
+	return NULL;
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,

arch/arm64/mm/dma-mapping.c

···
 
 #include <asm/cacheflush.h>
 
-static struct gen_pool *atomic_pool __ro_after_init;
-
-#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
-static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
-
-static int __init early_coherent_pool(char *p)
-{
-	atomic_pool_size = memparse(p, &p);
-	return 0;
-}
-early_param("coherent_pool", early_coherent_pool);
-
-static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
-{
-	unsigned long val;
-	void *ptr = NULL;
-
-	if (!atomic_pool) {
-		WARN(1, "coherent pool not initialised!\n");
-		return NULL;
-	}
-
-	val = gen_pool_alloc(atomic_pool, size);
-	if (val) {
-		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
-
-		*ret_page = phys_to_page(phys);
-		ptr = (void *)val;
-		memset(ptr, 0, size);
-	}
-
-	return ptr;
-}
-
-static bool __in_atomic_pool(void *start, size_t size)
-{
-	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
-}
-
-static int __free_from_pool(void *start, size_t size)
-{
-	if (!__in_atomic_pool(start, size))
-		return 0;
-
-	gen_pool_free(atomic_pool, (unsigned long)start, size);
-
-	return 1;
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t flags, unsigned long attrs)
-{
-	struct page *page;
-	void *ptr, *coherent_ptr;
-	pgprot_t prot = pgprot_writecombine(PAGE_KERNEL);
-
-	size = PAGE_ALIGN(size);
-
-	if (!gfpflags_allow_blocking(flags)) {
-		struct page *page = NULL;
-		void *addr = __alloc_from_pool(size, &page, flags);
-
-		if (addr)
-			*dma_handle = phys_to_dma(dev, page_to_phys(page));
-
-		return addr;
-	}
-
-	ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs);
-	if (!ptr)
-		goto no_mem;
-
-	/* remove any dirty cache lines on the kernel alias */
-	__dma_flush_area(ptr, size);
-
-	/* create a coherent mapping */
-	page = virt_to_page(ptr);
-	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
-						   prot, __builtin_return_address(0));
-	if (!coherent_ptr)
-		goto no_map;
-
-	return coherent_ptr;
-
-no_map:
-	dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs);
-no_mem:
-	return NULL;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	if (!__free_from_pool(vaddr, PAGE_ALIGN(size))) {
-		void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle));
-
-		vunmap(vaddr);
-		dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs);
-	}
-}
-
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
-		dma_addr_t dma_addr)
-{
-	return __phys_to_pfn(dma_to_phys(dev, dma_addr));
-}
-
 pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
 		unsigned long attrs)
 {
···
 		size_t size, enum dma_data_direction dir)
 {
 	__dma_unmap_area(phys_to_virt(paddr), size, dir);
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	__dma_flush_area(page_address(page), size);
 }
 
 #ifdef CONFIG_IOMMU_DMA
···
 }
 #endif /* CONFIG_IOMMU_DMA */
 
-static int __init atomic_pool_init(void)
-{
-	pgprot_t prot = __pgprot(PROT_NORMAL_NC);
-	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
-	struct page *page;
-	void *addr;
-	unsigned int pool_size_order = get_order(atomic_pool_size);
-
-	if (dev_get_cma_area(NULL))
-		page = dma_alloc_from_contiguous(NULL, nr_pages,
-						 pool_size_order, false);
-	else
-		page = alloc_pages(GFP_DMA32, pool_size_order);
-
-	if (page) {
-		int ret;
-		void *page_addr = page_address(page);
-
-		memset(page_addr, 0, atomic_pool_size);
-		__dma_flush_area(page_addr, atomic_pool_size);
-
-		atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
-		if (!atomic_pool)
-			goto free_page;
-
-		addr = dma_common_contiguous_remap(page, atomic_pool_size,
-					VM_USERMAP, prot, atomic_pool_init);
-
-		if (!addr)
-			goto destroy_genpool;
-
-		ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
-					page_to_phys(page),
-					atomic_pool_size, -1);
-		if (ret)
-			goto remove_mapping;
-
-		gen_pool_set_algo(atomic_pool,
-				  gen_pool_first_fit_order_align,
-				  NULL);
-
-		pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
-			atomic_pool_size / 1024);
-		return 0;
-	}
-	goto out;
-
-remove_mapping:
-	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
-destroy_genpool:
-	gen_pool_destroy(atomic_pool);
-	atomic_pool = NULL;
-free_page:
-	if (!dma_release_from_contiguous(NULL, page, nr_pages))
-		__free_pages(page, pool_size_order);
-out:
-	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
-		atomic_pool_size / 1024);
-	return -ENOMEM;
-}
-
-/********************************************
- * The following APIs are for dummy DMA ops *
- ********************************************/
-
-static void *__dummy_alloc(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flags,
-			   unsigned long attrs)
-{
-	return NULL;
-}
-
-static void __dummy_free(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle,
-			 unsigned long attrs)
-{
-}
-
-static int __dummy_mmap(struct device *dev,
-			struct vm_area_struct *vma,
-			void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			unsigned long attrs)
-{
-	return -ENXIO;
-}
-
-static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	return 0;
-}
-
-static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-}
-
-static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl,
-			  int nelems, enum dma_data_direction dir,
-			  unsigned long attrs)
-{
-	return 0;
-}
-
-static void __dummy_unmap_sg(struct device *dev,
-			     struct scatterlist *sgl, int nelems,
-			     enum dma_data_direction dir,
-			     unsigned long attrs)
-{
-}
-
-static void __dummy_sync_single(struct device *dev,
-				dma_addr_t dev_addr, size_t size,
-				enum dma_data_direction dir)
-{
-}
-
-static void __dummy_sync_sg(struct device *dev,
-			    struct scatterlist *sgl, int nelems,
-			    enum dma_data_direction dir)
-{
-}
-
-static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
-	return 1;
-}
-
-static int __dummy_dma_supported(struct device *hwdev, u64 mask)
-{
-	return 0;
-}
-
-const struct dma_map_ops dummy_dma_ops = {
-	.alloc                  = __dummy_alloc,
-	.free                   = __dummy_free,
-	.mmap                   = __dummy_mmap,
-	.map_page               = __dummy_map_page,
-	.unmap_page             = __dummy_unmap_page,
-	.map_sg                 = __dummy_map_sg,
-	.unmap_sg               = __dummy_unmap_sg,
-	.sync_single_for_cpu    = __dummy_sync_single,
-	.sync_single_for_device = __dummy_sync_single,
-	.sync_sg_for_cpu        = __dummy_sync_sg,
-	.sync_sg_for_device     = __dummy_sync_sg,
-	.mapping_error          = __dummy_mapping_error,
-	.dma_supported          = __dummy_dma_supported,
-};
-EXPORT_SYMBOL(dummy_dma_ops);
-
 static int __init arm64_dma_init(void)
 {
 	WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
 		   TAINT_CPU_OUT_OF_SPEC,
 		   "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
 		   ARCH_DMA_MINALIGN, cache_line_size());
-
-	return atomic_pool_init();
+	return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC));
 }
 arch_initcall(arm64_dma_init);
 
···
 			page = alloc_pages(gfp, get_order(size));
 			addr = page ? page_address(page) : NULL;
 		} else {
-			addr = __alloc_from_pool(size, &page, gfp);
+			addr = dma_alloc_from_pool(size, &page, gfp);
 		}
 		if (!addr)
 			return NULL;
 
 		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
-		if (iommu_dma_mapping_error(dev, *handle)) {
+		if (*handle == DMA_MAPPING_ERROR) {
 			if (coherent)
 				__free_pages(page, get_order(size));
 			else
-				__free_from_pool(addr, size);
+				dma_free_from_pool(addr, size);
 			addr = NULL;
 		}
 	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
···
 			return NULL;
 
 		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
-		if (iommu_dma_mapping_error(dev, *handle)) {
+		if (*handle == DMA_MAPPING_ERROR) {
 			dma_release_from_contiguous(dev, page,
 						    size >> PAGE_SHIFT);
 			return NULL;
···
 	 *   coherent devices.
 	 * Hence how dodgy the below logic looks...
 	 */
-	if (__in_atomic_pool(cpu_addr, size)) {
+	if (dma_in_atomic_pool(cpu_addr, size)) {
 		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
-		__free_from_pool(cpu_addr, size);
+		dma_free_from_pool(cpu_addr, size);
 	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
 		struct page *page = vmalloc_to_page(cpu_addr);
 
···
 	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
 
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    !iommu_dma_mapping_error(dev, dev_addr))
+	    dev_addr != DMA_MAPPING_ERROR)
 		__dma_map_area(page_address(page) + offset, size, dir);
 
 	return dev_addr;
···
 	.sync_sg_for_device = __iommu_sync_sg_for_device,
 	.map_resource = iommu_dma_map_resource,
 	.unmap_resource = iommu_dma_unmap_resource,
-	.mapping_error = iommu_dma_mapping_error,
 };
 
 static int __init __iommu_dma_init(void)
···
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	if (!dev->dma_ops)
-		dev->dma_ops = &swiotlb_dma_ops;
-
 	dev->dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
 

arch/c6x/Kconfig

···
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select CLKDEV_LOOKUP
-	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_TRACEHOOK

arch/c6x/mm/dma-coherent.c

···
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		gfp_t gfp, unsigned long attrs)
 {
+	void *ret;
 	u32 paddr;
 	int order;
 
···
 	if (!paddr)
 		return NULL;
 
-	return phys_to_virt(paddr);
+	ret = phys_to_virt(paddr);
+	memset(ret, 0, 1 << order);
+	return ret;
 }
 
 /*

arch/csky/Kconfig

···
 	select COMMON_CLK
 	select CLKSRC_MMIO
 	select CLKSRC_OF
-	select DMA_DIRECT_OPS
-	select DMA_NONCOHERENT_OPS
+	select DMA_DIRECT_REMAP
 	select IRQ_DOMAIN
 	select HANDLE_DOMAIN_IRQ
 	select DW_APB_TIMER_OF

arch/csky/mm/dma-mapping.c

···
 #include <linux/version.h>
 #include <asm/cache.h>
 
-static struct gen_pool *atomic_pool;
-static size_t atomic_pool_size __initdata = SZ_256K;
-
-static int __init early_coherent_pool(char *p)
-{
-	atomic_pool_size = memparse(p, &p);
-	return 0;
-}
-early_param("coherent_pool", early_coherent_pool);
-
 static int __init atomic_pool_init(void)
 {
-	struct page *page;
-	size_t size = atomic_pool_size;
-	void *ptr;
-	int ret;
-
-	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
-	if (!atomic_pool)
-		BUG();
-
-	page = alloc_pages(GFP_KERNEL | GFP_DMA, get_order(size));
-	if (!page)
-		BUG();
-
-	ptr = dma_common_contiguous_remap(page, size, VM_ALLOC,
-					  pgprot_noncached(PAGE_KERNEL),
-					  __builtin_return_address(0));
-	if (!ptr)
-		BUG();
-
-	ret = gen_pool_add_virt(atomic_pool, (unsigned long)ptr,
-				page_to_phys(page), atomic_pool_size, -1);
-	if (ret)
-		BUG();
-
-	gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL);
-
-	pr_info("DMA: preallocated %zu KiB pool for atomic coherent pool\n",
-		atomic_pool_size / 1024);
-
-	pr_info("DMA: vaddr: 0x%x phy: 0x%lx,\n", (unsigned int)ptr,
-		page_to_phys(page));
-
-	return 0;
+	return dma_atomic_pool_init(GFP_KERNEL, pgprot_noncached(PAGE_KERNEL));
 }
 postcore_initcall(atomic_pool_init);
 
-static void *csky_dma_alloc_atomic(struct device *dev, size_t size,
-				   dma_addr_t *dma_handle)
-{
-	unsigned long addr;
-
-	addr = gen_pool_alloc(atomic_pool, size);
-	if (addr)
-		*dma_handle = gen_pool_virt_to_phys(atomic_pool, addr);
-
-	return (void *)addr;
-}
-
-static void csky_dma_free_atomic(struct device *dev, size_t size, void *vaddr,
-				 dma_addr_t dma_handle, unsigned long attrs)
-{
-	gen_pool_free(atomic_pool, (unsigned long)vaddr, size);
-}
-
-static void __dma_clear_buffer(struct page *page, size_t size)
+void arch_dma_prep_coherent(struct page *page, size_t size)
 {
 	if (PageHighMem(page)) {
 		unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
···
 		memset(ptr, 0, size);
 		dma_wbinv_range((unsigned long)ptr, (unsigned long)ptr + size);
 	}
-}
-
-static void *csky_dma_alloc_nonatomic(struct device *dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t gfp,
-				      unsigned long attrs)
-{
-	void  *vaddr;
-	struct page *page;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	if (DMA_ATTR_NON_CONSISTENT & attrs) {
-		pr_err("csky %s can't support DMA_ATTR_NON_CONSISTENT.\n", __func__);
-		return NULL;
-	}
-
-	if (IS_ENABLED(CONFIG_DMA_CMA))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 gfp);
-	else
-		page = alloc_pages(gfp, get_order(size));
-
-	if (!page) {
-		pr_err("csky %s no more free pages.\n", __func__);
-		return NULL;
-	}
-
-	*dma_handle = page_to_phys(page);
-
-	__dma_clear_buffer(page, size);
-
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
-		return page;
-
-	vaddr = dma_common_contiguous_remap(page, PAGE_ALIGN(size), VM_USERMAP,
-		pgprot_noncached(PAGE_KERNEL), __builtin_return_address(0));
-	if (!vaddr)
-		BUG();
-
-	return vaddr;
-}
-
-static void csky_dma_free_nonatomic(
-	struct device *dev,
-	size_t size,
-	void *vaddr,
-	dma_addr_t dma_handle,
-	unsigned long attrs
-	)
-{
-	struct page *page = phys_to_page(dma_handle);
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	if ((unsigned int)vaddr >= VMALLOC_START)
-		dma_common_free_remap(vaddr, size, VM_USERMAP);
-
-	if (IS_ENABLED(CONFIG_DMA_CMA))
-		dma_release_from_contiguous(dev, page, count);
-	else
-		__free_pages(page, get_order(size));
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		     gfp_t gfp, unsigned long attrs)
-{
-	if (gfpflags_allow_blocking(gfp))
-		return csky_dma_alloc_nonatomic(dev, size, dma_handle, gfp,
-						attrs);
-	else
-		return csky_dma_alloc_atomic(dev, size, dma_handle);
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		   dma_addr_t dma_handle, unsigned long attrs)
-{
-	if (!addr_in_gen_pool(atomic_pool, (unsigned int) vaddr, size))
-		csky_dma_free_nonatomic(dev, size, vaddr, dma_handle, attrs);
-	else
-		csky_dma_free_atomic(dev, size, vaddr, dma_handle, attrs);
 }
 
 static inline void cache_op(phys_addr_t paddr, size_t size,

arch/h8300/Kconfig

···
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
-	select DMA_DIRECT_OPS
 
 config CPU_BIG_ENDIAN
 	def_bool y

arch/hexagon/Kconfig

···
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
-	select DMA_DIRECT_OPS
 	---help---
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.

arch/ia64/Kconfig

···
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_DMA_MARK_CLEAN
-	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select ARCH_DISCARD_MEMBLOCK
 	select GENERIC_IRQ_PROBE

arch/ia64/hp/common/hwsw_iommu.c

···
 const struct dma_map_ops *hwsw_dma_get_ops(struct device *dev)
 {
 	if (use_swiotlb(dev))
-		return &swiotlb_dma_ops;
+		return NULL;
 	return &sba_dma_ops;
 }
 EXPORT_SYMBOL(hwsw_dma_get_ops);

arch/ia64/hp/common/sba_iommu.c

···
 }
 
 /**
- * sba_map_single_attrs - map one buffer and return IOVA for DMA
+ * sba_map_page - map one buffer and return IOVA for DMA
  * @dev: instance of PCI owned by the driver that's asking.
- * @addr:  driver buffer to map.
- * @size:  number of bytes to map in driver buffer.
- * @dir:  R/W or both.
+ * @page: page to map
+ * @poff: offset into page
+ * @size: number of bytes to map
+ * @dir: dma direction
  * @attrs: optional dma attributes
  *
  * See Documentation/DMA-API-HOWTO.txt
···
  		** Device is bit capable of DMA'ing to the buffer...
 		** just return the PCI address of ptr
  		*/
-		DBG_BYPASS("sba_map_single_attrs() bypass mask/addr: "
+		DBG_BYPASS("sba_map_page() bypass mask/addr: "
 			   "0x%lx/0x%lx\n",
 		           to_pci_dev(dev)->dma_mask, pci_addr);
 		return pci_addr;
···
 
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	if (sba_check_pdir(ioc,"Check before sba_map_single_attrs()"))
+	if (sba_check_pdir(ioc,"Check before sba_map_page()"))
 		panic("Sanity check failed");
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
 
 	pide = sba_alloc_range(ioc, dev, size);
 	if (pide < 0)
-		return 0;
+		return DMA_MAPPING_ERROR;
 
 	iovp = (dma_addr_t) pide << iovp_shift;
 
···
 	/* form complete address */
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	sba_check_pdir(ioc,"Check after sba_map_single_attrs()");
+	sba_check_pdir(ioc,"Check after sba_map_page()");
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
 	return SBA_IOVA(ioc, iovp, offset);
-}
-
-static dma_addr_t sba_map_single_attrs(struct device *dev, void *addr,
-				       size_t size, enum dma_data_direction dir,
-				       unsigned long attrs)
-{
-	return sba_map_page(dev, virt_to_page(addr),
-			    (unsigned long)addr & ~PAGE_MASK, size, dir, attrs);
 }
 
 #ifdef ENABLE_MARK_CLEAN
···
 #endif
 
 /**
- * sba_unmap_single_attrs - unmap one IOVA and free resources
+ * sba_unmap_page - unmap one IOVA and free resources
  * @dev: instance of PCI owned by the driver that's asking.
  * @iova:  IOVA of driver buffer previously mapped.
  * @size:  number of bytes mapped in driver buffer.
···
 		/*
 		** Address does not fall w/in IOVA, must be bypassing
 		*/
-		DBG_BYPASS("sba_unmap_single_attrs() bypass addr: 0x%lx\n",
+		DBG_BYPASS("sba_unmap_page() bypass addr: 0x%lx\n",
 			   iova);
 
 #ifdef ENABLE_MARK_CLEAN
···
 #endif /* DELAYED_RESOURCE_CNT == 0 */
 }
 
-void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
-			    enum dma_data_direction dir, unsigned long attrs)
-{
-	sba_unmap_page(dev, iova, size, dir, attrs);
-}
-
 /**
  * sba_alloc_coherent - allocate/map shared mem for DMA
  * @dev: instance of PCI owned by the driver that's asking.
···
 sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		   gfp_t flags, unsigned long attrs)
 {
+	struct page *page;
 	struct ioc *ioc;
+	int node = -1;
 	void *addr;
 
 	ioc = GET_IOC(dev);
 	ASSERT(ioc);
-
 #ifdef CONFIG_NUMA
-	{
-		struct page *page;
-
-		page = alloc_pages_node(ioc->node, flags, get_order(size));
-		if (unlikely(!page))
-			return NULL;
-
-		addr = page_address(page);
-	}
-#else
-	addr = (void *) __get_free_pages(flags, get_order(size));
+	node = ioc->node;
 #endif
-	if (unlikely(!addr))
+
+	page = alloc_pages_node(node, flags, get_order(size));
+	if (unlikely(!page))
 		return NULL;
 
+	addr = page_address(page);
 	memset(addr, 0, size);
-	*dma_handle = virt_to_phys(addr);
+	*dma_handle = page_to_phys(page);
 
 #ifdef ALLOW_IOV_BYPASS
 	ASSERT(dev->coherent_dma_mask);
···
 	 * If device can't bypass or bypass is disabled, pass the 32bit fake
 	 * device to map single to get an iova mapping.
 	 */
-	*dma_handle = sba_map_single_attrs(&ioc->sac_only_dev->dev, addr,
-					   size, 0, 0);
-
+	*dma_handle = sba_map_page(&ioc->sac_only_dev->dev, page, 0, size,
+			DMA_BIDIRECTIONAL, 0);
+	if (dma_mapping_error(dev, *dma_handle))
+		return NULL;
 	return addr;
 }
 
···
 static void sba_free_coherent(struct device *dev, size_t size, void *vaddr,
 			      dma_addr_t dma_handle, unsigned long attrs)
 {
-	sba_unmap_single_attrs(dev, dma_handle, size, 0, 0);
+	sba_unmap_page(dev, dma_handle, size, 0, 0);
 	free_pages((unsigned long) vaddr, get_order(size));
 }
 
···
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {
 		sglist->dma_length = sglist->length;
-		sglist->dma_address = sba_map_single_attrs(dev, sba_sg_address(sglist), sglist->length, dir, attrs);
+		sglist->dma_address = sba_map_page(dev, sg_page(sglist),
+				sglist->offset, sglist->length, dir, attrs);
+		if (dma_mapping_error(dev, sglist->dma_address))
+			return 0;
 		return 1;
 	}
 
···
 
 	while (nents && sglist->dma_length) {
 
-		sba_unmap_single_attrs(dev, sglist->dma_address,
-				       sglist->dma_length, dir, attrs);
+		sba_unmap_page(dev, sglist->dma_address, sglist->dma_length,
+			       dir, attrs);
 		sglist = sg_next(sglist);
 		nents--;
 	}
···
 /* This has to run before acpi_scan_init(). */
 arch_initcall(acpi_sba_ioc_init_acpi);
 
-extern const struct dma_map_ops swiotlb_dma_ops;
-
 static int __init
 sba_init(void)
 {
···
 	 * a successful kdump kernel boot is to use the swiotlb.
 	 */
 	if (is_kdump_kernel()) {
-		dma_ops = &swiotlb_dma_ops;
+		dma_ops = NULL;
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to initialize software I/O TLB:"
 				  " Try machvec=dig boot option");
···
 		 * If we didn't find something sba_iommu can claim, we
 		 * need to setup the swiotlb and switch to the dig machvec.
 		 */
-		dma_ops = &swiotlb_dma_ops;
+		dma_ops = NULL;
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to find SBA IOMMU or initialize "
 			      "software I/O TLB: Try machvec=dig boot option");
···
 	return ((mask & 0xFFFFFFFFUL) == 0xFFFFFFFFUL);
 }
 
-static int sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
 __setup("nosbagart", nosbagart);
 
 static int __init
···
 	.map_sg			= sba_map_sg_attrs,
 	.unmap_sg		= sba_unmap_sg_attrs,
 	.dma_supported		= sba_dma_supported,
-	.mapping_error		= sba_dma_mapping_error,
 };
 
 void sba_dma_init(void)

arch/ia64/kernel/dma-mapping.c

···
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/swiotlb.h>
 #include <linux/export.h>
 
···
 EXPORT_SYMBOL(dma_get_ops);
 
 #ifdef CONFIG_SWIOTLB
+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);
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+		dma_addr_t dma_addr)
+{
+	return page_to_pfn(virt_to_page(cpu_addr));
+}
+
 void __init swiotlb_dma_init(void)
 {
-	dma_ops = &swiotlb_dma_ops;
 	swiotlb_init(1);
 }
 #endif

arch/ia64/mm/init.c

···
 #include <linux/kernel.h>
 #include <linux/init.h>
 
+#include <linux/dma-noncoherent.h>
 #include <linux/efi.h>
 #include <linux/elf.h>
 #include <linux/memblock.h>
···
  * 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
-dma_mark_clean(void *addr, size_t size)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	unsigned long pg_addr, end;
+	unsigned long pfn = PHYS_PFN(paddr);
 
-	pg_addr = PAGE_ALIGN((unsigned long) addr);
-	end = (unsigned long) addr + size;
-	while (pg_addr + PAGE_SIZE <= end) {
-		struct page *page = virt_to_page(pg_addr);
-		set_bit(PG_arch_1, &page->flags);
-		pg_addr += PAGE_SIZE;
-	}
+	do {
+		set_bit(PG_arch_1, &pfn_to_page(pfn)->flags);
+	} while (++pfn <= PHYS_PFN(paddr + size - 1));
 }
 
 inline void

arch/ia64/sn/pci/pci_dma.c

···
 
 	if (!dma_addr) {
 		printk(KERN_ERR "%s: out of ATEs\n", __func__);
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
···
 	}
 
 	return nhwentries;
-}
-
-static int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
 }
 
 static u64 sn_dma_get_required_mask(struct device *dev)
···
 	.unmap_page		= sn_dma_unmap_page,
 	.map_sg			= sn_dma_map_sg,
 	.unmap_sg		= sn_dma_unmap_sg,
-	.mapping_error		= sn_dma_mapping_error,
 	.dma_supported		= sn_dma_supported,
 	.get_required_mask	= sn_dma_get_required_mask,
 };

arch/m68k/Kconfig

···
 	select MODULES_USE_ELF_RELA
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
-	select DMA_DIRECT_OPS if HAS_DMA
 	select ARCH_DISCARD_MEMBLOCK
 
 config CPU_BIG_ENDIAN

arch/m68k/kernel/dma.c

···
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
-	page = alloc_pages(flag, order);
+	page = alloc_pages(flag | __GFP_ZERO, order);
 	if (!page)
 		return NULL;
 

arch/microblaze/Kconfig

···
 	select TIMER_OF
 	select CLONE_BACKWARDS3
 	select COMMON_CLK
-	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES

arch/microblaze/mm/consistent.c

···
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
-	vaddr = __get_free_pages(gfp, order);
+	vaddr = __get_free_pages(gfp | __GFP_ZERO, order);
 	if (!vaddr)
 		return NULL;
 

arch/mips/Kconfig

···
 	select CLONE_BACKWARDS
 	select CPU_NO_EFFICIENT_FFS if (TARGET_ISA_REV < 1)
 	select CPU_PM if CPU_IDLE
-	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE

arch/mips/include/asm/dma-mapping.h

···
 {
 #if defined(CONFIG_MACH_JAZZ)
 	return &jazz_dma_ops;
-#elif defined(CONFIG_SWIOTLB)
-	return &swiotlb_dma_ops;
 #else
-	return &dma_direct_ops;
+	return NULL;
 #endif
 }
 

arch/mips/include/asm/jazzdma.h

···
 #define VDMA_OFFSET(a)		((unsigned int)(a) & (VDMA_PAGESIZE-1))
 
 /*
- * error code returned by vdma_alloc()
- * (See also arch/mips/kernel/jazzdma.c)
- */
-#define VDMA_ERROR		0xffffffff
-
-/*
  * VDMA pagetable entry description
  */
 typedef volatile struct VDMA_PGTBL_ENTRY {

arch/mips/jazz/jazzdma.c

···
 		if (vdma_debug)
 			printk("vdma_alloc: Invalid physical address: %08lx\n",
 			       paddr);
-		return VDMA_ERROR;	/* invalid physical address */
+		return DMA_MAPPING_ERROR;	/* invalid physical address */
 	}
 	if (size > 0x400000 || size == 0) {
 		if (vdma_debug)
 			printk("vdma_alloc: Invalid size: %08lx\n", size);
-		return VDMA_ERROR;	/* invalid physical address */
+		return DMA_MAPPING_ERROR;	/* invalid physical address */
 	}
 
 	spin_lock_irqsave(&vdma_lock, flags);
···
 		       first < VDMA_PGTBL_ENTRIES) first++;
 		if (first + pages > VDMA_PGTBL_ENTRIES) {	/* nothing free */
 			spin_unlock_irqrestore(&vdma_lock, flags);
-			return VDMA_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		last = first + 1;
···
 		return NULL;
 
 	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
-	if (*dma_handle == VDMA_ERROR) {
+	if (*dma_handle == DMA_MAPPING_ERROR) {
 		dma_direct_free_pages(dev, size, ret, *dma_handle, attrs);
 		return NULL;
 	}
···
 			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
 				dir);
 		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
-		if (sg->dma_address == VDMA_ERROR)
+		if (sg->dma_address == DMA_MAPPING_ERROR)
 			return 0;
 		sg_dma_len(sg) = sg->length;
 	}
···
 		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
 }
 
-static int jazz_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == VDMA_ERROR;
-}
-
 const struct dma_map_ops jazz_dma_ops = {
 	.alloc			= jazz_dma_alloc,
 	.free			= jazz_dma_free,
···
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
 	.dma_supported		= dma_direct_supported,
 	.cache_sync		= arch_dma_cache_sync,
-	.mapping_error		= jazz_dma_mapping_error,
 };
 EXPORT_SYMBOL(jazz_dma_ops);

arch/nds32/Kconfig

···
 	select CLKSRC_MMIO
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS

arch/nios2/Kconfig

···
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_NO_SWAP
-	select DMA_DIRECT_OPS
 	select TIMER_OF
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS

arch/openrisc/Kconfig

···
 config OPENRISC
 	def_bool y
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select DMA_DIRECT_OPS
 	select OF
 	select OF_EARLY_FLATTREE
 	select IRQ_DOMAIN

arch/openrisc/kernel/dma.c

···
 		.mm = &init_mm
 	};
 
-	page = alloc_pages_exact(size, gfp);
+	page = alloc_pages_exact(size, gfp | __GFP_ZERO);
 	if (!page)
 		return NULL;
 

arch/parisc/Kconfig

···
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_NO_SG_CHAIN
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
···
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select DMA_DIRECT_OPS
 	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH

arch/parisc/kernel/pci-dma.c

···
 	order = get_order(size);
 	size = 1 << (order + PAGE_SHIFT);
 	vaddr = pcxl_alloc_range(size);
-	paddr = __get_free_pages(flag, order);
+	paddr = __get_free_pages(flag | __GFP_ZERO, order);
 	flush_kernel_dcache_range(paddr, size);
 	paddr = __pa(paddr);
 	map_uncached_pages(vaddr, size, paddr);
···
 	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
 		return NULL;
 
-	addr = (void *)__get_free_pages(flag, get_order(size));
+	addr = (void *)__get_free_pages(flag | __GFP_ZERO, get_order(size));
 	if (addr)
 		*dma_handle = (dma_addr_t)virt_to_phys(addr);
 

arch/parisc/kernel/setup.c

···
 
 	case pcxl2:
 		pa7300lc_init();
-	case pcxl: /* falls through */
-	case pcxs:
-	case pcxt:
-		hppa_dma_ops = &dma_direct_ops;
 		break;
 	default:
 		break;

arch/powerpc/Kconfig

···
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC64
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64

arch/powerpc/include/asm/dma-mapping.h

···
 }
 
 #define HAVE_ARCH_DMA_SET_MASK 1
-extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
 extern u64 __dma_get_required_mask(struct device *dev);
 

arch/powerpc/include/asm/iommu.h

···
 
 #ifdef CONFIG_PPC64
 
-#define IOMMU_MAPPING_ERROR		(~(dma_addr_t)0x0)
-
 static inline void set_iommu_table_base(struct device *dev,
 					struct iommu_table *base)
 {
···
 {
 }
 #endif /* !CONFIG_IOMMU_API */
-
-int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 #else
 

arch/powerpc/kernel/dma-iommu.c

···
 	return mask;
 }
 
-int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == IOMMU_MAPPING_ERROR;
-}
-
 struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
···
 	.map_page		= dma_iommu_map_page,
 	.unmap_page		= dma_iommu_unmap_page,
 	.get_required_mask	= dma_iommu_get_required_mask,
-	.mapping_error		= dma_iommu_mapping_error,
 };

arch/powerpc/kernel/dma-swiotlb.c

···
 	.alloc = __dma_nommu_alloc_coherent,
 	.free = __dma_nommu_free_coherent,
 	.mmap = dma_nommu_mmap_coherent,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.map_sg = dma_direct_map_sg,
+	.unmap_sg = dma_direct_unmap_sg,
 	.dma_supported = swiotlb_dma_supported,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.mapping_error = dma_direct_mapping_error,
+	.map_page = dma_direct_map_page,
+	.unmap_page = dma_direct_unmap_page,
+	.sync_single_for_cpu = dma_direct_sync_single_for_cpu,
+	.sync_single_for_device = dma_direct_sync_single_for_device,
+	.sync_sg_for_cpu = dma_direct_sync_sg_for_cpu,
+	.sync_sg_for_device = dma_direct_sync_sg_for_device,
 	.get_required_mask = swiotlb_powerpc_get_required,
 };
 

arch/powerpc/kernel/iommu.c

···
 	if (unlikely(npages == 0)) {
 		if (printk_ratelimit())
 			WARN_ON(1);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	if (should_fail_iommu(dev))
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	/*
 	 * We don't need to disable preemption here because any CPU can
···
 		} else {
 			/* Give up */
 			spin_unlock_irqrestore(&(pool->lock), flags);
-			return IOMMU_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 	}
 
···
 			      unsigned long attrs)
 {
 	unsigned long entry;
-	dma_addr_t ret = IOMMU_MAPPING_ERROR;
+	dma_addr_t ret = DMA_MAPPING_ERROR;
 	int build_fail;
 
 	entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
 
-	if (unlikely(entry == IOMMU_MAPPING_ERROR))
-		return IOMMU_MAPPING_ERROR;
+	if (unlikely(entry == DMA_MAPPING_ERROR))
+		return DMA_MAPPING_ERROR;
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
 	ret = entry << tbl->it_page_shift;	/* Set the return dma address */
···
 
 	/* tbl->it_ops->set() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
-	 * IOMMU_MAPPING_ERROR. For all other errors the functionality is
+	 * DMA_MAPPING_ERROR. For all other errors the functionality is
 	 * not altered.
 	 */
 	if (unlikely(build_fail)) {
 		__iommu_free(tbl, ret, npages);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	/* Flush/invalidate TLB caches if necessary */
···
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
 		/* Handle failure */
-		if (unlikely(entry == IOMMU_MAPPING_ERROR)) {
+		if (unlikely(entry == DMA_MAPPING_ERROR)) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())
 				dev_info(dev, "iommu_alloc failed, tbl %p "
···
 	 */
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = IOMMU_MAPPING_ERROR;
+		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
···
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IOMMU_PAGE_SIZE(tbl));
 			__iommu_free(tbl, vaddr, npages);
-			s->dma_address = IOMMU_MAPPING_ERROR;
+			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
···
 			  unsigned long mask, enum dma_data_direction direction,
 			  unsigned long attrs)
 {
-	dma_addr_t dma_handle = IOMMU_MAPPING_ERROR;
+	dma_addr_t dma_handle = DMA_MAPPING_ERROR;
 	void *vaddr;
 	unsigned long uaddr;
 	unsigned int npages, align;
···
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
 					 mask >> tbl->it_page_shift, align,
 					 attrs);
-		if (dma_handle == IOMMU_MAPPING_ERROR) {
+		if (dma_handle == DMA_MAPPING_ERROR) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())  {
 				dev_info(dev, "iommu_alloc failed, tbl %p "
···
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
-	if (mapping == IOMMU_MAPPING_ERROR) {
+	if (mapping == DMA_MAPPING_ERROR) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}

arch/powerpc/platforms/cell/iommu.c

···
 	.dma_supported  = dma_suported_and_switch,
 	.map_page       = dma_fixed_map_page,
 	.unmap_page     = dma_fixed_unmap_page,
-	.mapping_error	= dma_iommu_mapping_error,
 };
 
 static void cell_dma_dev_setup(struct device *dev)

arch/powerpc/platforms/pseries/vio.c

···
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl;
-	dma_addr_t ret = IOMMU_MAPPING_ERROR;
+	dma_addr_t ret = DMA_MAPPING_ERROR;
 
 	tbl = get_iommu_table_base(dev);
 	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
···
 	.unmap_page        = vio_dma_iommu_unmap_page,
 	.dma_supported     = vio_dma_iommu_dma_supported,
 	.get_required_mask = vio_dma_get_required_mask,
-	.mapping_error	   = dma_iommu_mapping_error,
 };
 
 /**

arch/riscv/Kconfig

···
 	select ARCH_WANT_FRAME_POINTERS
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select DMA_DIRECT_OPS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES
 	select GENERIC_IRQ_SHOW

arch/riscv/include/asm/dma-mapping.h

···
-// SPDX-License-Identifier: GPL-2.0
-#ifndef _RISCV_ASM_DMA_MAPPING_H
-#define _RISCV_ASM_DMA_MAPPING_H 1
-
-#ifdef CONFIG_SWIOTLB
-#include <linux/swiotlb.h>
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &swiotlb_dma_ops;
-}
-#else
-#include <asm-generic/dma-mapping.h>
-#endif /* CONFIG_SWIOTLB */
-
-#endif /* _RISCV_ASM_DMA_MAPPING_H */

arch/s390/Kconfig

···
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
···
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
-	select DMA_DIRECT_OPS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS

arch/s390/pci/pci_dma.c

···
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
 
-#define S390_MAPPING_ERROR		(~(dma_addr_t) 0x0)
-
 static struct kmem_cache *dma_region_table_cache;
 static struct kmem_cache *dma_page_table_cache;
 static int s390_iommu_strict;
···
 
 out_error:
 	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
-	return S390_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size)
···
 	/* This rounds up number of pages based on size and offset */
 	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
 	dma_addr = dma_alloc_address(dev, nr_pages);
-	if (dma_addr == S390_MAPPING_ERROR) {
+	if (dma_addr == DMA_MAPPING_ERROR) {
 		ret = -ENOSPC;
 		goto out_err;
 	}
···
 out_err:
 	zpci_err("map error:\n");
 	zpci_err_dma(ret, pa);
-	return S390_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
···
 	dma_addr_t map;
 
 	size = PAGE_ALIGN(size);
-	page = alloc_pages(flag, get_order(size));
+	page = alloc_pages(flag | __GFP_ZERO, get_order(size));
 	if (!page)
 		return NULL;
 
···
 	int ret;
 
 	dma_addr_base = dma_alloc_address(dev, nr_pages);
-	if (dma_addr_base == S390_MAPPING_ERROR)
+	if (dma_addr_base == DMA_MAPPING_ERROR)
 		return -ENOMEM;
 
 	dma_addr = dma_addr_base;
···
 	for (i = 1; i < nr_elements; i++) {
 		s = sg_next(s);
 
-		s->dma_address = S390_MAPPING_ERROR;
+		s->dma_address = DMA_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) ||
···
 	}
 }
 	
-static int s390_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == S390_MAPPING_ERROR;
-}
-
 int zpci_dma_init_device(struct zpci_dev *zdev)
 {
 	int rc;
···
 	.unmap_sg	= s390_dma_unmap_sg,
 	.map_page	= s390_dma_map_pages,
 	.unmap_page	= s390_dma_unmap_pages,
-	.mapping_error	= s390_mapping_error,
 	/* dma_supported is unconditionally true without a callback */
 };
 EXPORT_SYMBOL_GPL(s390_pci_dma_ops);

arch/sh/Kconfig

···
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select HAVE_PATA_PLATFORM
 	select CLKDEV_LOOKUP
-	select DMA_DIRECT_OPS
 	select HAVE_IDE if HAS_IOPORT_MAP
 	select HAVE_MEMBLOCK_NODE_MAP
 	select ARCH_DISCARD_MEMBLOCK

arch/sparc/Kconfig

···
 	select MODULES_USE_ELF_RELA
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
-	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
 	select LOCKDEP_SMALL if LOCKDEP
 	select NEED_DMA_MAP_STATE
···
 config SPARC32
 	def_bool !64BIT
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
-	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64
 	select CLZ_TAB
 	select HAVE_UID16

arch/sparc/include/asm/dma-mapping.h

···
 #ifndef ___ASM_SPARC_DMA_MAPPING_H
 #define ___ASM_SPARC_DMA_MAPPING_H
 
-#include <linux/scatterlist.h>
-#include <linux/mm.h>
-#include <linux/dma-debug.h>
+#include <asm/cpu_type.h>
 
 extern const struct dma_map_ops *dma_ops;
 
···
 {
 #ifdef CONFIG_SPARC_LEON
 	if (sparc_cpu_model == sparc_leon)
-		return &dma_direct_ops;
+		return NULL;
 #endif
 #if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
 	if (bus == &pci_bus_type)
-		return &dma_direct_ops;
+		return NULL;
 #endif
 	return dma_ops;
 }

arch/sparc/include/asm/dma.h

···
 #endif
 
 #ifdef CONFIG_SPARC32
-
-/* Routines for data transfer buffers. */
 struct device;
-struct scatterlist;
 
-struct sparc32_dma_ops {
-	__u32 (*get_scsi_one)(struct device *, char *, unsigned long);
-	void (*get_scsi_sgl)(struct device *, struct scatterlist *, int);
-	void (*release_scsi_one)(struct device *, __u32, unsigned long);
-	void (*release_scsi_sgl)(struct device *, struct scatterlist *,int);
-#ifdef CONFIG_SBUS
-	int (*map_dma_area)(struct device *, dma_addr_t *, unsigned long, unsigned long, int);
-	void (*unmap_dma_area)(struct device *, unsigned long, int);
-#endif
-};
-extern const struct sparc32_dma_ops *sparc32_dma_ops;
-
-#define mmu_get_scsi_one(dev,vaddr,len) \
-	sparc32_dma_ops->get_scsi_one(dev, vaddr, len)
-#define mmu_get_scsi_sgl(dev,sg,sz) \
-	sparc32_dma_ops->get_scsi_sgl(dev, sg, sz)
-#define mmu_release_scsi_one(dev,vaddr,len) \
-	sparc32_dma_ops->release_scsi_one(dev, vaddr,len)
-#define mmu_release_scsi_sgl(dev,sg,sz) \
-	sparc32_dma_ops->release_scsi_sgl(dev, sg, sz)
-
-#ifdef CONFIG_SBUS
-/*
- * mmu_map/unmap are provided by iommu/iounit; Invalid to call on IIep.
- *
- * The mmu_map_dma_area establishes two mappings in one go.
- * These mappings point to pages normally mapped at 'va' (linear address).
- * First mapping is for CPU visible address at 'a', uncached.
- * This is an alias, but it works because it is an uncached mapping.
- * Second mapping is for device visible address, or "bus" address.
- * The bus address is returned at '*pba'.
- *
- * These functions seem distinct, but are hard to split.
- * On sun4m, page attributes depend on the CPU type, so we have to
- * know if we are mapping RAM or I/O, so it has to be an additional argument
- * to a separate mapping function for CPU visible mappings.
- */
-#define sbus_map_dma_area(dev,pba,va,a,len) \
-	sparc32_dma_ops->map_dma_area(dev, pba, va, a, len)
-#define sbus_unmap_dma_area(dev,ba,len) \
-	sparc32_dma_ops->unmap_dma_area(dev, ba, len)
-#endif /* CONFIG_SBUS */
-
+unsigned long sparc_dma_alloc_resource(struct device *dev, size_t len);
+bool sparc_dma_free_resource(void *cpu_addr, size_t size);
 #endif
 
 #endif /* !(_ASM_SPARC_DMA_H) */

arch/sparc/include/asm/leon.h

···
 #define _pfn_valid(pfn)	 ((pfn < last_valid_pfn) && (pfn >= PFN(phys_base)))
 #define _SRMMU_PTE_PMASK_LEON 0xffffffff
 
+/*
+ * On LEON PCI Memory space is mapped 1:1 with physical address space.
+ *
+ * I/O space is located at low 64Kbytes in PCI I/O space. The I/O addresses
+ * are converted into CPU addresses to virtual addresses that are mapped with
+ * MMU to the PCI Host PCI I/O space window which are translated to the low
+ * 64Kbytes by the Host controller.
+ */
+
 #endif

arch/sparc/include/asm/pci.h

···
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ___ASM_SPARC_PCI_H
 #define ___ASM_SPARC_PCI_H
-#if defined(__sparc__) && defined(__arch64__)
-#include <asm/pci_64.h>
+
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+ * already-configured bus numbers - to be used for buggy BIOSes
+ * or architectures with incomplete PCI setup by the loader.
+ */
+#define pcibios_assign_all_busses()	0
+
+#define PCIBIOS_MIN_IO		0UL
+#define PCIBIOS_MIN_MEM		0UL
+
+#define PCI_IRQ_NONE		0xffffffff
+
+
+#ifdef CONFIG_SPARC64
+
+/* PCI IOMMU mapping bypass support. */
+
+/* PCI 64-bit addressing works for all slots on all controller
+ * types on sparc64.  However, it requires that the device
+ * can drive enough of the 64 bits.
+ */
+#define PCI64_REQUIRED_MASK	(~(u64)0)
+#define PCI64_ADDR_BASE		0xfffc000000000000UL
+
+/* Return the index of the PCI controller for device PDEV. */
+int pci_domain_nr(struct pci_bus *bus);
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	return 1;
+}
+
+/* Platform support for /proc/bus/pci/X/Y mmap()s. */
+#define HAVE_PCI_MMAP
+#define arch_can_pci_mmap_io()	1
+#define HAVE_ARCH_PCI_GET_UNMAPPED_AREA
+#define get_pci_unmapped_area get_fb_unmapped_area
+
+#define HAVE_ARCH_PCI_RESOURCE_TO_USER
+#endif /* CONFIG_SPARC64 */
+
+#if defined(CONFIG_SPARC64) || defined(CONFIG_LEON_PCI)
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return PCI_IRQ_NONE;
+}
 #else
-#include <asm/pci_32.h>
+#include <asm-generic/pci.h>
 #endif
-#endif
+
+#endif /* ___ASM_SPARC_PCI_H */

arch/sparc/include/asm/pci_32.h

···
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __SPARC_PCI_H
-#define __SPARC_PCI_H
-
-#ifdef __KERNEL__
-
-#include <linux/dma-mapping.h>
-
-/* Can be used to override the logic in pci_scan_bus for skipping
- * already-configured bus numbers - to be used for buggy BIOSes
- * or architectures with incomplete PCI setup by the loader.
- */
-#define pcibios_assign_all_busses()	0
-
-#define PCIBIOS_MIN_IO		0UL
-#define PCIBIOS_MIN_MEM		0UL
-
-#define PCI_IRQ_NONE		0xffffffff
-
-#endif /* __KERNEL__ */
-
-#ifndef CONFIG_LEON_PCI
-/* generic pci stuff */
-#include <asm-generic/pci.h>
-#else
-/*
- * On LEON PCI Memory space is mapped 1:1 with physical address space.
- *
- * I/O space is located at low 64Kbytes in PCI I/O space. The I/O addresses
- * are converted into CPU addresses to virtual addresses that are mapped with
- * MMU to the PCI Host PCI I/O space window which are translated to the low
- * 64Kbytes by the Host controller.
- */
-
-static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
-{
-	return PCI_IRQ_NONE;
-}
-#endif
-
-#endif /* __SPARC_PCI_H */

arch/sparc/include/asm/pci_64.h

···
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __SPARC64_PCI_H
-#define __SPARC64_PCI_H
-
-#ifdef __KERNEL__
-
-#include <linux/dma-mapping.h>
-
-/* Can be used to override the logic in pci_scan_bus for skipping
- * already-configured bus numbers - to be used for buggy BIOSes
- * or architectures with incomplete PCI setup by the loader.
- */
-#define pcibios_assign_all_busses()	0
-
-#define PCIBIOS_MIN_IO		0UL
-#define PCIBIOS_MIN_MEM		0UL
-
-#define PCI_IRQ_NONE		0xffffffff
-
-/* PCI IOMMU mapping bypass support. */
-
-/* PCI 64-bit addressing works for all slots on all controller
- * types on sparc64.  However, it requires that the device
- * can drive enough of the 64 bits.
- */
-#define PCI64_REQUIRED_MASK	(~(u64)0)
-#define PCI64_ADDR_BASE		0xfffc000000000000UL
-
-/* Return the index of the PCI controller for device PDEV. */
-
-int pci_domain_nr(struct pci_bus *bus);
-static inline int pci_proc_domain(struct pci_bus *bus)
-{
-	return 1;
-}
-
-/* Platform support for /proc/bus/pci/X/Y mmap()s. */
-
-#define HAVE_PCI_MMAP
-#define arch_can_pci_mmap_io()	1
-#define HAVE_ARCH_PCI_GET_UNMAPPED_AREA
-#define get_pci_unmapped_area get_fb_unmapped_area
-
-static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
-{
-	return PCI_IRQ_NONE;
-}
-
-#define HAVE_ARCH_PCI_RESOURCE_TO_USER
-#endif /* __KERNEL__ */
-
-#endif /* __SPARC64_PCI_H */

arch/sparc/kernel/iommu.c

···
 bad_no_ctx:
 	if (printk_ratelimit())
 		WARN_ON(1);
-	return SPARC_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static void strbuf_flush(struct strbuf *strbuf, struct iommu *iommu,
···
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = SPARC_MAPPING_ERROR;
+		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
···
 			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 
-			s->dma_address = SPARC_MAPPING_ERROR;
+			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
···
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-static int dma_4u_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == SPARC_MAPPING_ERROR;
-}
-
 static int dma_4u_supported(struct device *dev, u64 device_mask)
 {
 	struct iommu *iommu = dev->archdata.iommu;
···
 	.sync_single_for_cpu	= dma_4u_sync_single_for_cpu,
 	.sync_sg_for_cpu	= dma_4u_sync_sg_for_cpu,
 	.dma_supported		= dma_4u_supported,
-	.mapping_error		= dma_4u_mapping_error,
 };
 
 const struct dma_map_ops *dma_ops = &sun4u_dma_ops;

arch/sparc/kernel/iommu_common.h

···
 	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 }
 
-#define SPARC_MAPPING_ERROR	(~(dma_addr_t)0x0)
-
 #endif /* _IOMMU_COMMON_H */

arch/sparc/kernel/ioport.c

···
 #include <asm/io-unit.h>
 #include <asm/leon.h>
 
-const struct sparc32_dma_ops *sparc32_dma_ops;
-
 /* This function must make sure that caches and memory are coherent after DMA
  * On LEON systems without cache snooping it flushes the entire D-CACHE.
  */
···
 	release_resource(res);
 }
 
+unsigned long sparc_dma_alloc_resource(struct device *dev, size_t len)
+{
+	struct resource *res;
+
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return 0;
+	res->name = dev->of_node->full_name;
+
+	if (allocate_resource(&_sparc_dvma, res, len, _sparc_dvma.start,
+			      _sparc_dvma.end, PAGE_SIZE, NULL, NULL) != 0) {
+		printk("%s: cannot occupy 0x%zx", __func__, len);
+		kfree(res);
+		return 0;
+	}
+
+	return res->start;
+}
+
+bool sparc_dma_free_resource(void *cpu_addr, size_t size)
+{
+	unsigned long addr = (unsigned long)cpu_addr;
+	struct resource *res;
+
+	res = lookup_resource(&_sparc_dvma, addr);
+	if (!res) {
+		printk("%s: cannot free %p\n", __func__, cpu_addr);
+		return false;
+	}
+
+	if ((addr & (PAGE_SIZE - 1)) != 0) {
+		printk("%s: unaligned va %p\n", __func__, cpu_addr);
+		return false;
+	}
+
+	size = PAGE_ALIGN(size);
+	if (resource_size(res) != size) {
+		printk("%s: region 0x%lx asked 0x%zx\n",
+			__func__, (long)resource_size(res), size);
+		return false;
+	}
+
+	release_resource(res);
+	kfree(res);
+	return true;
+}
+
 #ifdef CONFIG_SBUS
 
 void sbus_set_sbus64(struct device *dev, int x)
···
 	printk("sbus_set_sbus64: unsupported\n");
 }
 EXPORT_SYMBOL(sbus_set_sbus64);
-
-/*
- * Allocate a chunk of memory suitable for DMA.
- * Typically devices use them for control blocks.
- * CPU may access them without any explicit flushing.
- */
-static void *sbus_alloc_coherent(struct device *dev, size_t len,
-				 dma_addr_t *dma_addrp, gfp_t gfp,
-				 unsigned long attrs)
-{
-	struct platform_device *op = to_platform_device(dev);
-	unsigned long len_total = PAGE_ALIGN(len);
-	unsigned long va;
-	struct resource *res;
-	int order;
-
-	/* XXX why are some lengths signed, others unsigned? */
-	if (len <= 0) {
-		return NULL;
-	}
-	/* XXX So what is maxphys for us and how do drivers know it? */
-	if (len > 256*1024) {			/* __get_free_pages() limit */
-		return NULL;
-	}
-
-	order = get_order(len_total);
-	va = __get_free_pages(gfp, order);
-	if (va == 0)
-		goto err_nopages;
-
-	if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL)
-		goto err_nomem;
-
-	if (allocate_resource(&_sparc_dvma, res, len_total,
-	    _sparc_dvma.start, _sparc_dvma.end, PAGE_SIZE, NULL, NULL) != 0) {
-		printk("sbus_alloc_consistent: cannot occupy 0x%lx", len_total);
-		goto err_nova;
-	}
-
-	// XXX The sbus_map_dma_area does this for us below, see comments.
-	// srmmu_mapiorange(0, virt_to_phys(va), res->start, len_total);
-	/*
-	 * XXX That's where sdev would be used. Currently we load
-	 * all iommu tables with the same translations.
-	 */
-	if (sbus_map_dma_area(dev, dma_addrp, va, res->start, len_total) != 0)
-		goto err_noiommu;
-
-	res->name = op->dev.of_node->full_name;
-
-	return (void *)(unsigned long)res->start;
-
-err_noiommu:
-	release_resource(res);
-err_nova:
-	kfree(res);
-err_nomem:
-	free_pages(va, order);
-err_nopages:
-	return NULL;
-}
-
-static void sbus_free_coherent(struct device *dev, size_t n, void *p,
-			       dma_addr_t ba, unsigned long attrs)
-{
-	struct resource *res;
-	struct page *pgv;
-
-	if ((res = lookup_resource(&_sparc_dvma,
-	    (unsigned long)p)) == NULL) {
-		printk("sbus_free_consistent: cannot free %p\n", p);
-		return;
-	}
-
-	if (((unsigned long)p & (PAGE_SIZE-1)) != 0) {
-		printk("sbus_free_consistent: unaligned va %p\n", p);
-		return;
-	}
-
-	n = PAGE_ALIGN(n);
-	if (resource_size(res) != n) {
-		printk("sbus_free_consistent: region 0x%lx asked 0x%zx\n",
-		    (long)resource_size(res), n);
-		return;
-	}
-
-	release_resource(res);
-	kfree(res);
-
-	pgv = virt_to_page(p);
-	sbus_unmap_dma_area(dev, ba, n);
-
-	__free_pages(pgv, get_order(n));
-}
-
-/*
- * Map a chunk of memory so that devices can see it.
- * CPU view of this memory may be inconsistent with
- * a device view and explicit flushing is necessary.
- */
-static dma_addr_t sbus_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t len,
-				enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	void *va = page_address(page) + offset;
-
-	/* XXX why are some lengths signed, others unsigned? */
-	if (len <= 0) {
-		return 0;
-	}
-	/* XXX So what is maxphys for us and how do drivers know it? */
-	if (len > 256*1024) {			/* __get_free_pages() limit */
-		return 0;
-	}
-	return mmu_get_scsi_one(dev, va, len);
-}
-
-static void sbus_unmap_page(struct device *dev, dma_addr_t ba, size_t n,
-			    enum dma_data_direction dir, unsigned long attrs)
-{
-	mmu_release_scsi_one(dev, ba, n);
-}
-
-static int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n,
-		       enum dma_data_direction dir, unsigned long attrs)
-{
-	mmu_get_scsi_sgl(dev, sg, n);
-	return n;
-}
-
-static void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n,
-			  enum dma_data_direction dir, unsigned long attrs)
-{
-	mmu_release_scsi_sgl(dev, sg, n);
-}
-
-static void sbus_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				 int n,	enum dma_data_direction dir)
-{
-	BUG();
-}
-
-static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-				    int n, enum dma_data_direction dir)
-{
-	BUG();
-}
-
-static int sbus_dma_supported(struct device *dev, u64 mask)
-{
-	return 0;
-}
-
-static const struct dma_map_ops sbus_dma_ops = {
-	.alloc			= sbus_alloc_coherent,
-	.free			= sbus_free_coherent,
-	.map_page		= sbus_map_page,
-	.unmap_page		= sbus_unmap_page,
-	.map_sg			= sbus_map_sg,
-	.unmap_sg		= sbus_unmap_sg,
-	.sync_sg_for_cpu	= sbus_sync_sg_for_cpu,
-	.sync_sg_for_device	= sbus_sync_sg_for_device,
-	.dma_supported		= sbus_dma_supported,
-};
 
 static int __init sparc_register_ioport(void)
 {
···
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
-	unsigned long len_total = PAGE_ALIGN(size);
+	unsigned long addr;
 	void *va;
-	struct resource *res;
-	int order;
 
-	if (size == 0) {
+	if (!size || size > 256 * 1024)	/* __get_free_pages() limit */
+		return NULL;
+
+	size = PAGE_ALIGN(size);
+	va = (void *) __get_free_pages(gfp | __GFP_ZERO, get_order(size));
+	if (!va) {
+		printk("%s: no %zd pages\n", __func__, size >> PAGE_SHIFT);
 		return NULL;
 	}
-	if (size > 256*1024) {			/* __get_free_pages() limit */
-		return NULL;
-	}
 
-	order = get_order(len_total);
-	va = (void *) __get_free_pages(gfp, order);
-	if (va == NULL) {
-		printk("%s: no %ld pages\n", __func__, len_total>>PAGE_SHIFT);
-		goto err_nopages;
-	}
-
-	if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL) {
-		printk("%s: no core\n", __func__);
+	addr = sparc_dma_alloc_resource(dev, size);
+	if (!addr)
 		goto err_nomem;
-	}
 
-	if (allocate_resource(&_sparc_dvma, res, len_total,
-	    _sparc_dvma.start, _sparc_dvma.end, PAGE_SIZE, NULL, NULL) != 0) {
-		printk("%s: cannot occupy 0x%lx", __func__, len_total);
-		goto err_nova;
-	}
-	srmmu_mapiorange(0, virt_to_phys(va), res->start, len_total);
+	srmmu_mapiorange(0, virt_to_phys(va), addr, size);
 
 	*dma_handle = virt_to_phys(va);
-	return (void *) res->start;
+	return (void *)addr;
 
-err_nova:
-	kfree(res);
 err_nomem:
-	free_pages((unsigned long)va, order);
-err_nopages:
+	free_pages((unsigned long)va, get_order(size));
 	return NULL;
 }
 
···
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
-	struct resource *res;
-
-	if ((res = lookup_resource(&_sparc_dvma,
-	    (unsigned long)cpu_addr)) == NULL) {
-		printk("%s: cannot free %p\n", __func__, cpu_addr);
+	if (!sparc_dma_free_resource(cpu_addr, PAGE_ALIGN(size)))
 		return;
-	}
-
-	if (((unsigned long)cpu_addr & (PAGE_SIZE-1)) != 0) {
-		printk("%s: unaligned va %p\n", __func__, cpu_addr);
-		return;
-	}
-
-	size = PAGE_ALIGN(size);
-	if (resource_size(res) != size) {
-		printk("%s: region 0x%lx asked 0x%zx\n", __func__,
-		    (long)resource_size(res), size);
-		return;
-	}
 
 	dma_make_coherent(dma_addr, size);
 	srmmu_unmapiorange((unsigned long)cpu_addr, size);
-
-	release_resource(res);
-	kfree(res);
 	free_pages((unsigned long)phys_to_virt(dma_addr), get_order(size));
 }
 
···
 		dma_make_coherent(paddr, PAGE_ALIGN(size));
 }
 
-const struct dma_map_ops *dma_ops = &sbus_dma_ops;
+const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 #ifdef CONFIG_PROC_FS

arch/sparc/kernel/pci_sun4v.c

···
 bad:
 	if (printk_ratelimit())
 		WARN_ON(1);
-	return SPARC_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 
 iommu_map_fail:
 	local_irq_restore(flags);
 	iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE);
-	return SPARC_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
···
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = SPARC_MAPPING_ERROR;
+		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
···
 			iommu_tbl_range_free(tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 			/* XXX demap? XXX */
-			s->dma_address = SPARC_MAPPING_ERROR;
+			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
···
 	return pci64_dma_supported(to_pci_dev(dev), device_mask);
 }
 
-static int dma_4v_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == SPARC_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops sun4v_dma_ops = {
 	.alloc				= dma_4v_alloc_coherent,
 	.free				= dma_4v_free_coherent,
···
 	.map_sg				= dma_4v_map_sg,
 	.unmap_sg			= dma_4v_unmap_sg,
 	.dma_supported			= dma_4v_supported,
-	.mapping_error			= dma_4v_mapping_error,
 };
 
 static void pci_sun4v_scan_bus(struct pci_pbm_info *pbm, struct device *parent)

arch/sparc/mm/io-unit.c

···
 #include <linux/mm.h>
 #include <linux/highmem.h>	/* pte_offset_map => kmap_atomic */
 #include <linux/bitops.h>
-#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
···
 	return vaddr;
 }
 
-static __u32 iounit_get_scsi_one(struct device *dev, char *vaddr, unsigned long len)
+static dma_addr_t iounit_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t len, enum dma_data_direction dir,
+		unsigned long attrs)
 {
+	void *vaddr = page_address(page) + offset;
 	struct iounit_struct *iounit = dev->archdata.iommu;
 	unsigned long ret, flags;
 	
+	/* XXX So what is maxphys for us and how do drivers know it? */
+	if (!len || len > 256 * 1024)
+		return DMA_MAPPING_ERROR;
+
 	spin_lock_irqsave(&iounit->lock, flags);
 	ret = iounit_get_area(iounit, (unsigned long)vaddr, len);
 	spin_unlock_irqrestore(&iounit->lock, flags);
 	return ret;
 }
 
-static void iounit_get_scsi_sgl(struct device *dev, struct scatterlist *sg, int sz)
+static int iounit_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
+	struct scatterlist *sg;
 	unsigned long flags;
+	int i;
 
 	/* FIXME: Cache some resolved pages - often several sg entries are to the same page */
 	spin_lock_irqsave(&iounit->lock, flags);
-	while (sz != 0) {
-		--sz;
+	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = iounit_get_area(iounit, (unsigned long) sg_virt(sg), sg->length);
 		sg->dma_length = sg->length;
-		sg = sg_next(sg);
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
+	return nents;
 }
 
-static void iounit_release_scsi_one(struct device *dev, __u32 vaddr, unsigned long len)
+static void iounit_unmap_page(struct device *dev, dma_addr_t vaddr, size_t len,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
 	unsigned long flags;
···
 	spin_unlock_irqrestore(&iounit->lock, flags);
 }
 
-static void iounit_release_scsi_sgl(struct device *dev, struct scatterlist *sg, int sz)
+static void iounit_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
-	unsigned long flags;
-	unsigned long vaddr, len;
+	unsigned long flags, vaddr, len;
+	struct scatterlist *sg;
+	int i;
 
 	spin_lock_irqsave(&iounit->lock, flags);
-	while (sz != 0) {
-		--sz;
+	for_each_sg(sgl, sg, nents, i) {
 		len = ((sg->dma_address & ~PAGE_MASK) + sg->length + (PAGE_SIZE-1)) >> PAGE_SHIFT;
 		vaddr = (sg->dma_address - IOUNIT_DMA_BASE) >> PAGE_SHIFT;
 		IOD(("iounit_release %08lx-%08lx\n", (long)vaddr, (long)len+vaddr));
 		for (len += vaddr; vaddr < len; vaddr++)
 			clear_bit(vaddr, iounit->bmap);
-		sg = sg_next(sg);
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
 }
 
 #ifdef CONFIG_SBUS
-static int iounit_map_dma_area(struct device *dev, dma_addr_t *pba, unsigned long va, unsigned long addr, int len)
+static void *iounit_alloc(struct device *dev, size_t len,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
-	unsigned long page, end;
+	unsigned long va, addr, page, end, ret;
 	pgprot_t dvma_prot;
 	iopte_t __iomem *iopte;
 
-	*pba = addr;
+	/* XXX So what is maxphys for us and how do drivers know it? */
+	if (!len || len > 256 * 1024)
+		return NULL;
+
+	len = PAGE_ALIGN(len);
+	va = __get_free_pages(gfp | __GFP_ZERO, get_order(len));
+	if (!va)
+		return NULL;
+
+	addr = ret = sparc_dma_alloc_resource(dev, len);
+	if (!addr)
+		goto out_free_pages;
+	*dma_handle = addr;
 
 	dvma_prot = __pgprot(SRMMU_CACHE | SRMMU_ET_PTE | SRMMU_PRIV);
 	end = PAGE_ALIGN((addr + len));
···
 	flush_cache_all();
 	flush_tlb_all();
 
-	return 0;
+	return (void *)ret;
+
+out_free_pages:
+	free_pages(va, get_order(len));
+	return NULL;
 }
 
-static void iounit_unmap_dma_area(struct device *dev, unsigned long addr, int len)
+static void iounit_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs)
 {
 	/* XXX Somebody please fill this in */
 }
 #endif
 
-static const struct sparc32_dma_ops iounit_dma_ops = {
-	.get_scsi_one		= iounit_get_scsi_one,
-	.get_scsi_sgl		= iounit_get_scsi_sgl,
-	.release_scsi_one	= iounit_release_scsi_one,
-	.release_scsi_sgl	= iounit_release_scsi_sgl,
+static const struct dma_map_ops iounit_dma_ops = {
 #ifdef CONFIG_SBUS
-	.map_dma_area		= iounit_map_dma_area,
-	.unmap_dma_area		= iounit_unmap_dma_area,
+	.alloc			= iounit_alloc,
+	.free			= iounit_free,
 #endif
+	.map_page		= iounit_map_page,
+	.unmap_page		= iounit_unmap_page,
+	.map_sg			= iounit_map_sg,
+	.unmap_sg		= iounit_unmap_sg,
 };
 
 void __init ld_mmu_iounit(void)
 {
-	sparc32_dma_ops = &iounit_dma_ops;
+	dma_ops = &iounit_dma_ops;
 }

arch/sparc/mm/iommu.c

···
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/highmem.h>	/* pte_offset_map => kmap_atomic */
-#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
···
 	return busa0;
 }
 
-static u32 iommu_get_scsi_one(struct device *dev, char *vaddr, unsigned int len)
+static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t len)
 {
-	unsigned long off;
-	int npages;
-	struct page *page;
-	u32 busa;
-
-	off = (unsigned long)vaddr & ~PAGE_MASK;
-	npages = (off + len + PAGE_SIZE-1) >> PAGE_SHIFT;
-	page = virt_to_page((unsigned long)vaddr & PAGE_MASK);
-	busa = iommu_get_one(dev, page, npages);
-	return busa + off;
+	void *vaddr = page_address(page) + offset;
+	unsigned long off = (unsigned long)vaddr & ~PAGE_MASK;
+	unsigned long npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	
+	/* XXX So what is maxphys for us and how do drivers know it? */
+	if (!len || len > 256 * 1024)
+		return DMA_MAPPING_ERROR;
+	return iommu_get_one(dev, virt_to_page(vaddr), npages) + off;
 }
 
-static __u32 iommu_get_scsi_one_gflush(struct device *dev, char *vaddr, unsigned long len)
+static dma_addr_t sbus_iommu_map_page_gflush(struct device *dev,
+		struct page *page, unsigned long offset, size_t len,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	flush_page_for_dma(0);
-	return iommu_get_scsi_one(dev, vaddr, len);
+	return __sbus_iommu_map_page(dev, page, offset, len);
 }
 
-static __u32 iommu_get_scsi_one_pflush(struct device *dev, char *vaddr, unsigned long len)
+static dma_addr_t sbus_iommu_map_page_pflush(struct device *dev,
+		struct page *page, unsigned long offset, size_t len,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	unsigned long page = ((unsigned long) vaddr) & PAGE_MASK;
+	void *vaddr = page_address(page) + offset;
+	unsigned long p = ((unsigned long)vaddr) & PAGE_MASK;
 
-	while(page < ((unsigned long)(vaddr + len))) {
-		flush_page_for_dma(page);
-		page += PAGE_SIZE;
+	while (p < (unsigned long)vaddr + len) {
+		flush_page_for_dma(p);
+		p += PAGE_SIZE;
 	}
-	return iommu_get_scsi_one(dev, vaddr, len);
+
+	return __sbus_iommu_map_page(dev, page, offset, len);
 }
 
-static void iommu_get_scsi_sgl_gflush(struct device *dev, struct scatterlist *sg, int sz)
+static int sbus_iommu_map_sg_gflush(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	int n;
+	struct scatterlist *sg;
+	int i, n;
 
 	flush_page_for_dma(0);
-	while (sz != 0) {
-		--sz;
+
+	for_each_sg(sgl, sg, nents, i) {
 		n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT;
 		sg->dma_address = iommu_get_one(dev, sg_page(sg), n) + sg->offset;
 		sg->dma_length = sg->length;
-		sg = sg_next(sg);
 	}
+
+	return nents;
 }
 
-static void iommu_get_scsi_sgl_pflush(struct device *dev, struct scatterlist *sg, int sz)
+static int sbus_iommu_map_sg_pflush(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long page, oldpage = 0;
-	int n, i;
+	struct scatterlist *sg;
+	int i, j, n;
 
-	while(sz != 0) {
-		--sz;
-
+	for_each_sg(sgl, sg, nents, j) {
 		n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT;
 
 		/*
···
 
 		sg->dma_address = iommu_get_one(dev, sg_page(sg), n) + sg->offset;
 		sg->dma_length = sg->length;
-		sg = sg_next(sg);
 	}
+
+	return nents;
 }
 
 static void iommu_release_one(struct device *dev, u32 busa, int npages)
···
 	bit_map_clear(&iommu->usemap, ioptex, npages);
 }
 
-static void iommu_release_scsi_one(struct device *dev, __u32 vaddr, unsigned long len)
+static void sbus_iommu_unmap_page(struct device *dev, dma_addr_t dma_addr,
+		size_t len, enum dma_data_direction dir, unsigned long attrs)
 {
-	unsigned long off;
+	unsigned long off = dma_addr & ~PAGE_MASK;
 	int npages;
 
-	off = vaddr & ~PAGE_MASK;
 	npages = (off + len + PAGE_SIZE-1) >> PAGE_SHIFT;
-	iommu_release_one(dev, vaddr & PAGE_MASK, npages);
+	iommu_release_one(dev, dma_addr & PAGE_MASK, npages);
 }
 
-static void iommu_release_scsi_sgl(struct device *dev, struct scatterlist *sg, int sz)
+static void sbus_iommu_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	int n;
+	struct scatterlist *sg;
+	int i, n;
 
-	while(sz != 0) {
-		--sz;
-
+	for_each_sg(sgl, sg, nents, i) {
 		n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT;
 		iommu_release_one(dev, sg->dma_address & PAGE_MASK, n);
 		sg->dma_address = 0x21212121;
-		sg = sg_next(sg);
 	}
 }
 
 #ifdef CONFIG_SBUS
-static int iommu_map_dma_area(struct device *dev, dma_addr_t *pba, unsigned long va,
-			      unsigned long addr, int len)
+static void *sbus_iommu_alloc(struct device *dev, size_t len,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct iommu_struct *iommu = dev->archdata.iommu;
-	unsigned long page, end;
+	unsigned long va, addr, page, end, ret;
 	iopte_t *iopte = iommu->page_table;
 	iopte_t *first;
 	int ioptex;
+
+	/* XXX So what is maxphys for us and how do drivers know it? */
+	if (!len || len > 256 * 1024)
+		return NULL;
+
+	len = PAGE_ALIGN(len);
+	va = __get_free_pages(gfp | __GFP_ZERO, get_order(len));
+	if (va == 0)
+		return NULL;
+
+	addr = ret = sparc_dma_alloc_resource(dev, len);
+	if (!addr)
+		goto out_free_pages;
 
 	BUG_ON((va & ~PAGE_MASK) != 0);
 	BUG_ON((addr & ~PAGE_MASK) != 0);
···
 	flush_tlb_all();
 	iommu_invalidate(iommu->regs);
 
-	*pba = iommu->start + (ioptex << PAGE_SHIFT);
-	return 0;
+	*dma_handle = iommu->start + (ioptex << PAGE_SHIFT);
+	return (void *)ret;
+
+out_free_pages:
+	free_pages(va, get_order(len));
+	return NULL;
 }
 
-static void iommu_unmap_dma_area(struct device *dev, unsigned long busa, int len)
+static void sbus_iommu_free(struct device *dev, size_t len, void *cpu_addr,
+			       dma_addr_t busa, unsigned long attrs)
 {
 	struct iommu_struct *iommu = dev->archdata.iommu;
 	iopte_t *iopte = iommu->page_table;
-	unsigned long end;
+	struct page *page = virt_to_page(cpu_addr);
 	int ioptex = (busa - iommu->start) >> PAGE_SHIFT;
+	unsigned long end;
+
+	if (!sparc_dma_free_resource(cpu_addr, len))
+		return;
 
 	BUG_ON((busa & ~PAGE_MASK) != 0);
 	BUG_ON((len & ~PAGE_MASK) != 0);
···
 	flush_tlb_all();
 	iommu_invalidate(iommu->regs);
 	bit_map_clear(&iommu->usemap, ioptex, len >> PAGE_SHIFT);
+
+	__free_pages(page, get_order(len));
 }
 #endif
 
-static const struct sparc32_dma_ops iommu_dma_gflush_ops = {
-	.get_scsi_one		= iommu_get_scsi_one_gflush,
-	.get_scsi_sgl		= iommu_get_scsi_sgl_gflush,
-	.release_scsi_one	= iommu_release_scsi_one,
-	.release_scsi_sgl	= iommu_release_scsi_sgl,
+static const struct dma_map_ops sbus_iommu_dma_gflush_ops = {
 #ifdef CONFIG_SBUS
-	.map_dma_area		= iommu_map_dma_area,
-	.unmap_dma_area		= iommu_unmap_dma_area,
+	.alloc			= sbus_iommu_alloc,
+	.free			= sbus_iommu_free,
 #endif
+	.map_page		= sbus_iommu_map_page_gflush,
+	.unmap_page		= sbus_iommu_unmap_page,
+	.map_sg			= sbus_iommu_map_sg_gflush,
+	.unmap_sg		= sbus_iommu_unmap_sg,
 };
 
-static const struct sparc32_dma_ops iommu_dma_pflush_ops = {
-	.get_scsi_one		= iommu_get_scsi_one_pflush,
-	.get_scsi_sgl		= iommu_get_scsi_sgl_pflush,
-	.release_scsi_one	= iommu_release_scsi_one,
-	.release_scsi_sgl	= iommu_release_scsi_sgl,
+static const struct dma_map_ops sbus_iommu_dma_pflush_ops = {
 #ifdef CONFIG_SBUS
-	.map_dma_area		= iommu_map_dma_area,
-	.unmap_dma_area		= iommu_unmap_dma_area,
+	.alloc			= sbus_iommu_alloc,
+	.free			= sbus_iommu_free,
 #endif
+	.map_page		= sbus_iommu_map_page_pflush,
+	.unmap_page		= sbus_iommu_unmap_page,
+	.map_sg			= sbus_iommu_map_sg_pflush,
+	.unmap_sg		= sbus_iommu_unmap_sg,
 };
 
 void __init ld_mmu_iommu(void)
 {
 	if (flush_page_for_dma_global) {
 		/* flush_page_for_dma flushes everything, no matter of what page is it */
-		sparc32_dma_ops = &iommu_dma_gflush_ops;
+		dma_ops = &sbus_iommu_dma_gflush_ops;
 	} else {
-		sparc32_dma_ops = &iommu_dma_pflush_ops;
+		dma_ops = &sbus_iommu_dma_pflush_ops;
 	}
 
 	if (viking_mxcc_present || srmmu_modtype == HyperSparc) {

arch/unicore32/Kconfig

···
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
-	select DMA_DIRECT_OPS
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2

arch/x86/Kconfig

···
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
···
 	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select CLOCKSOURCE_WATCHDOG
 	select DCACHE_WORD_ACCESS
-	select DMA_DIRECT_OPS
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
 	select GENERIC_CLOCKEVENTS

arch/x86/kernel/amd_gart_64.c

···
 
 static u32 *iommu_gatt_base;		/* Remapping table */
 
-static dma_addr_t bad_dma_addr;
-
 /*
  * If this is disabled the IOMMU will use an optimized flushing strategy
  * of only flushing when an mapping is reused. With it true the GART is
···
 #define GPTE_ENCODE(x) \
 	(((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT)
 #define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28))
-
-#define EMERGENCY_PAGES 32 /* = 128KB */
 
 #ifdef CONFIG_AGP
 #define AGPEXTERN extern
···
 
 #ifdef CONFIG_IOMMU_LEAK
 /* Debugging aid for drivers that don't free their IOMMU tables */
-static int leak_trace;
-static int iommu_leak_pages = 20;
-
 static void dump_leak(void)
 {
 	static int dump;
···
 	 */
 
 	dev_err(dev, "PCI-DMA: Out of IOMMU space for %lu bytes\n", size);
-
-	if (size > PAGE_SIZE*EMERGENCY_PAGES) {
-		if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
-			panic("PCI-DMA: Memory would be corrupted\n");
-		if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
-			panic(KERN_ERR
-				"PCI-DMA: Random memory would be DMAed\n");
-	}
 #ifdef CONFIG_IOMMU_LEAK
 	dump_leak();
 #endif
···
 	int i;
 
 	if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
-		return bad_dma_addr;
+		return DMA_MAPPING_ERROR;
 
 	iommu_page = alloc_iommu(dev, npages, align_mask);
 	if (iommu_page == -1) {
···
 		if (panic_on_overflow)
 			panic("dma_map_area overflow %lu bytes\n", size);
 		iommu_full(dev, size, dir);
-		return bad_dma_addr;
+		return DMA_MAPPING_ERROR;
 	}
 
 	for (i = 0; i < npages; i++) {
···
 	int npages;
 	int i;
 
-	if (dma_addr < iommu_bus_base + EMERGENCY_PAGES*PAGE_SIZE ||
+	if (dma_addr == DMA_MAPPING_ERROR ||
 	    dma_addr >= iommu_bus_base + iommu_size)
 		return;
 
···
 
 		if (nonforced_iommu(dev, addr, s->length)) {
 			addr = dma_map_area(dev, addr, s->length, dir, 0);
-			if (addr == bad_dma_addr) {
+			if (addr == DMA_MAPPING_ERROR) {
 				if (i > 0)
 					gart_unmap_sg(dev, sg, i, dir, 0);
 				nents = 0;
···
 
 	iommu_full(dev, pages << PAGE_SHIFT, dir);
 	for_each_sg(sg, s, nents, i)
-		s->dma_address = bad_dma_addr;
+		s->dma_address = DMA_MAPPING_ERROR;
 	return 0;
 }
 
···
 	*dma_addr = dma_map_area(dev, virt_to_phys(vaddr), size,
 			DMA_BIDIRECTIONAL, (1UL << get_order(size)) - 1);
 	flush_gart();
-	if (unlikely(*dma_addr == bad_dma_addr))
+	if (unlikely(*dma_addr == DMA_MAPPING_ERROR))
 		goto out_free;
 	return vaddr;
 out_free:
···
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
 	dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
-}
-
-static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return (dma_addr == bad_dma_addr);
 }
 
 static int no_agp;
···
 	.unmap_page			= gart_unmap_page,
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
-	.mapping_error			= gart_mapping_error,
 	.dma_supported			= dma_direct_supported,
 };
 
···
 	unsigned long aper_base, aper_size;
 	unsigned long start_pfn, end_pfn;
 	unsigned long scratch;
-	long i;
 
 	if (!amd_nb_has_feature(AMD_NB_GART))
 		return 0;
···
 	if (!iommu_gart_bitmap)
 		panic("Cannot allocate iommu bitmap\n");
 
-#ifdef CONFIG_IOMMU_LEAK
-	if (leak_trace) {
-		int ret;
-
-		ret = dma_debug_resize_entries(iommu_pages);
-		if (ret)
-			pr_debug("PCI-DMA: Cannot trace all the entries\n");
-	}
-#endif
-
-	/*
-	 * Out of IOMMU space handling.
-	 * Reserve some invalid pages at the beginning of the GART.
-	 */
-	bitmap_set(iommu_gart_bitmap, 0, EMERGENCY_PAGES);
-
 	pr_info("PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n",
 	       iommu_size >> 20);
 
 	agp_memory_reserved	= iommu_size;
 	iommu_start		= aper_size - iommu_size;
 	iommu_bus_base		= info.aper_base + iommu_start;
-	bad_dma_addr		= iommu_bus_base;
 	iommu_gatt_base		= agp_gatt_table + (iommu_start>>PAGE_SHIFT);
 
 	/*
···
 	if (!scratch)
 		panic("Cannot allocate iommu scratch page");
 	gart_unmapped_entry = GPTE_ENCODE(__pa(scratch));
-	for (i = EMERGENCY_PAGES; i < iommu_pages; i++)
-		iommu_gatt_base[i] = gart_unmapped_entry;
 
 	flush_gart();
 	dma_ops = &gart_dma_ops;
···
 {
 	int arg;
 
-#ifdef CONFIG_IOMMU_LEAK
-	if (!strncmp(p, "leak", 4)) {
-		leak_trace = 1;
-		p += 4;
-		if (*p == '=')
-			++p;
-		if (isdigit(*p) && get_option(&p, &arg))
-			iommu_leak_pages = arg;
-	}
-#endif
 	if (isdigit(*p) && get_option(&p, &arg))
 		iommu_size = arg;
 	if (!strncmp(p, "fullflush", 9))

arch/x86/kernel/pci-calgary_64.c

···
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
-#define CALGARY_MAPPING_ERROR	0
-
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
 #else
···
 
 #define PHB_DEBUG_STUFF_OFFSET	0x0020
 
-#define EMERGENCY_PAGES 32 /* = 128KB */
-
 unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED;
 static int translate_empty_slots __read_mostly = 0;
 static int calgary_detected __read_mostly = 0;
···
 			if (panic_on_overflow)
 				panic("Calgary: fix the allocator.\n");
 			else
-				return CALGARY_MAPPING_ERROR;
+				return DMA_MAPPING_ERROR;
 		}
 	}
 
···
 	dma_addr_t ret;
 
 	entry = iommu_range_alloc(dev, tbl, npages);
-
-	if (unlikely(entry == CALGARY_MAPPING_ERROR)) {
+	if (unlikely(entry == DMA_MAPPING_ERROR)) {
 		pr_warn("failed to allocate %u pages in iommu %p\n",
 			npages, tbl);
-		return CALGARY_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	/* set the return dma address */
···
 	unsigned int npages)
 {
 	unsigned long entry;
-	unsigned long badend;
 	unsigned long flags;
 
 	/* were we called with bad_dma_address? */
-	badend = CALGARY_MAPPING_ERROR + (EMERGENCY_PAGES * PAGE_SIZE);
-	if (unlikely(dma_addr < badend)) {
+	if (unlikely(dma_addr == DMA_MAPPING_ERROR)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
 		return;
···
 		npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE);
 
 		entry = iommu_range_alloc(dev, tbl, npages);
-		if (entry == CALGARY_MAPPING_ERROR) {
+		if (entry == DMA_MAPPING_ERROR) {
 			/* makes sure unmap knows to stop */
 			s->dma_length = 0;
 			goto error;
···
 error:
 	calgary_unmap_sg(dev, sg, nelems, dir, 0);
 	for_each_sg(sg, s, nelems, i) {
-		sg->dma_address = CALGARY_MAPPING_ERROR;
+		sg->dma_address = DMA_MAPPING_ERROR;
 		sg->dma_length = 0;
 	}
 	return 0;
···
 
 	/* set up tces to cover the allocated range */
 	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-	if (mapping == CALGARY_MAPPING_ERROR)
+	if (mapping == DMA_MAPPING_ERROR)
 		goto free;
 	*dma_handle = mapping;
 	return ret;
···
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static int calgary_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == CALGARY_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops calgary_dma_ops = {
 	.alloc = calgary_alloc_coherent,
 	.free = calgary_free_coherent,
···
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
 	.unmap_page = calgary_unmap_page,
-	.mapping_error = calgary_mapping_error,
 	.dma_supported = dma_direct_supported,
 };
 
···
 	unsigned int npages;
 	u64 start;
 	struct iommu_table *tbl = pci_iommu(dev->bus);
-
-	/* reserve EMERGENCY_PAGES from bad_dma_address and up */
-	iommu_range_reserve(tbl, CALGARY_MAPPING_ERROR, EMERGENCY_PAGES);
 
 	/* avoid the BIOS/VGA first 640KB-1MB region */
 	/* for CalIOC2 - avoid the entire first MB */

arch/x86/kernel/pci-dma.c

···
 
 static bool disable_dac_quirk __read_mostly;
 
-const struct dma_map_ops *dma_ops = &dma_direct_ops;
+const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 #ifdef CONFIG_IOMMU_DEBUG

arch/x86/kernel/pci-swiotlb.c

···
 
 void __init pci_swiotlb_init(void)
 {
-	if (swiotlb) {
+	if (swiotlb)
 		swiotlb_init(0);
-		dma_ops = &swiotlb_dma_ops;
-	}
 }
 
 void __init pci_swiotlb_late_init(void)

arch/x86/mm/mem_encrypt.c

···
 	swiotlb_update_mem_attributes();
 
 	/*
-	 * With SEV, DMA operations cannot use encryption, we need to use
-	 * SWIOTLB to bounce buffer DMA operation.
-	 */
-	if (sev_active())
-		dma_ops = &swiotlb_dma_ops;
-
-	/*
 	 * With SEV, we need to unroll the rep string I/O instructions.
 	 */
 	if (sev_active())

arch/x86/pci/sta2x11-fixup.c

···
 		return;
 	pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
 	pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
-	pdev->dev.dma_ops = &swiotlb_dma_ops;
 	pdev->dev.archdata.is_sta2x11 = true;
 
 	/* We must enable all devices as master, for audio DMA to work */

arch/xtensa/Kconfig

···
 # SPDX-License-Identifier: GPL-2.0
 config XTENSA
 	def_bool y
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
···
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select DMA_DIRECT_OPS
+	select DMA_REMAP if MMU
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_SHOW

arch/xtensa/kernel/pci-dma.c

···
 						 flag & __GFP_NOWARN);
 
 	if (!page)
-		page = alloc_pages(flag, get_order(size));
+		page = alloc_pages(flag | __GFP_ZERO, get_order(size));
 
 	if (!page)
 		return NULL;

drivers/acpi/scan.c

···
 	const struct iommu_ops *iommu;
 	u64 dma_addr = 0, size = 0;
 
+	if (attr == DEV_DMA_NOT_SUPPORTED) {
+		set_dma_ops(dev, &dma_dummy_ops);
+		return 0;
+	}
+
 	iort_dma_setup(dev, &dma_addr, &size);
 
 	iommu = iort_iommu_configure(dev);

drivers/base/platform.c

···
 		ret = of_dma_configure(dev, dev->of_node, true);
 	} else if (has_acpi_companion(dev)) {
 		attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
-		if (attr != DEV_DMA_NOT_SUPPORTED)
-			ret = acpi_dma_configure(dev, attr);
+		ret = acpi_dma_configure(dev, attr);
 	}
 
 	return ret;
···
 	of_platform_register_reconfig_notifier();
 	return error;
 }
-
-#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK
-static u64 dma_default_get_required_mask(struct device *dev)
-{
-	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
-	u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
-	u64 mask;
-
-	if (!high_totalram) {
-		/* convert to mask just covering totalram */
-		low_totalram = (1 << (fls(low_totalram) - 1));
-		low_totalram += low_totalram - 1;
-		mask = low_totalram;
-	} else {
-		high_totalram = (1 << (fls(high_totalram) - 1));
-		high_totalram += high_totalram - 1;
-		mask = (((u64)high_totalram) << 32) + 0xffffffff;
-	}
-	return mask;
-}
-
-u64 dma_get_required_mask(struct device *dev)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (ops->get_required_mask)
-		return ops->get_required_mask(dev);
-	return dma_default_get_required_mask(dev);
-}
-EXPORT_SYMBOL_GPL(dma_get_required_mask);
-#endif
 
 static __initdata LIST_HEAD(early_platform_driver_list);
 static __initdata LIST_HEAD(early_platform_device_list);

drivers/gpu/drm/vmwgfx/vmwgfx_drv.c

···
 
 	dev_priv->map_mode = vmw_dma_map_populate;
 
-	if (dma_ops->sync_single_for_cpu)
+	if (dma_ops && dma_ops->sync_single_for_cpu)
 		dev_priv->map_mode = vmw_dma_alloc_coherent;
 #ifdef CONFIG_SWIOTLB
 	if (swiotlb_nr_tbl() == 0)

drivers/iommu/amd_iommu.c

···
 #include "amd_iommu_types.h"
 #include "irq_remapping.h"
 
-#define AMD_IOMMU_MAPPING_ERROR	0
-
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
 #define LOOP_TIMEOUT	100000
···
 				dev_name(dev));
 
 		iommu_ignore_device(dev);
-		dev->dma_ops = &dma_direct_ops;
+		dev->dma_ops = NULL;
 		goto out;
 	}
 	init_iommu_group(dev);
···
 	paddr &= PAGE_MASK;
 
 	address = dma_ops_alloc_iova(dev, dma_dom, pages, dma_mask);
-	if (address == AMD_IOMMU_MAPPING_ERROR)
+	if (!address)
 		goto out;
 
 	prot = dir2prot(direction);
···
 
 	dma_ops_free_iova(dma_dom, address, pages);
 
-	return AMD_IOMMU_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /*
···
 	if (PTR_ERR(domain) == -EINVAL)
 		return (dma_addr_t)paddr;
 	else if (IS_ERR(domain))
-		return AMD_IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	dma_mask = *dev->dma_mask;
 	dma_dom = to_dma_ops_domain(domain);
···
 	npages = sg_num_pages(dev, sglist, nelems);
 
 	address = dma_ops_alloc_iova(dev, dma_dom, npages, dma_mask);
-	if (address == AMD_IOMMU_MAPPING_ERROR)
+	if (address == DMA_MAPPING_ERROR)
 		goto out_err;
 
 	prot = dir2prot(direction);
···
 	*dma_addr = __map_single(dev, dma_dom, page_to_phys(page),
 				 size, DMA_BIDIRECTIONAL, dma_mask);
 
-	if (*dma_addr == AMD_IOMMU_MAPPING_ERROR)
+	if (*dma_addr == DMA_MAPPING_ERROR)
 		goto out_free;
 
 	return page_address(page);
···
 	return check_device(dev);
 }
 
-static int amd_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == AMD_IOMMU_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops amd_iommu_dma_ops = {
 	.alloc		= alloc_coherent,
 	.free		= free_coherent,
···
 	.map_sg		= map_sg,
 	.unmap_sg	= unmap_sg,
 	.dma_supported	= amd_iommu_dma_supported,
-	.mapping_error	= amd_iommu_mapping_error,
 };
 
 static int init_reserved_iova_ranges(void)
···
 {
 	swiotlb        = (iommu_pass_through || sme_me_mask) ? 1 : 0;
 	iommu_detected = 1;
-
-	/*
-	 * In case we don't initialize SWIOTLB (actually the common case
-	 * when AMD IOMMU is enabled and SME is not active), make sure there
-	 * are global dma_ops set as a fall-back for devices not handled by
-	 * this driver (for example non-PCI devices). When SME is active,
-	 * make sure that swiotlb variable remains set so the global dma_ops
-	 * continue to be SWIOTLB.
-	 */
-	if (!swiotlb)
-		dma_ops = &dma_direct_ops;
 
 	if (amd_iommu_unmap_flush)
 		pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n");

drivers/iommu/dma-iommu.c

···
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
 
-#define IOMMU_MAPPING_ERROR	0
-
 struct iommu_dma_msi_page {
 	struct list_head	list;
 	dma_addr_t		iova;
···
 {
 	__iommu_dma_unmap(iommu_get_dma_domain(dev), *handle, size);
 	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
-	*handle = IOMMU_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 }
 
 /**
···
 	dma_addr_t iova;
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 
-	*handle = IOMMU_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 
 	min_size = alloc_sizes & -alloc_sizes;
 	if (min_size < PAGE_SIZE) {
···
 
 	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
 	if (!iova)
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
 		iommu_dma_free_iova(cookie, iova, size);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 	return iova + iova_off;
 }
···
 
 		s->offset += s_iova_off;
 		s->length = s_length;
-		sg_dma_address(s) = IOMMU_MAPPING_ERROR;
+		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 
 		/*
···
 	int i;
 
 	for_each_sg(sg, s, nents, i) {
-		if (sg_dma_address(s) != IOMMU_MAPPING_ERROR)
+		if (sg_dma_address(s) != DMA_MAPPING_ERROR)
 			s->offset += sg_dma_address(s);
 		if (sg_dma_len(s))
 			s->length = sg_dma_len(s);
-		sg_dma_address(s) = IOMMU_MAPPING_ERROR;
+		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 	}
 }
···
 	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
 }
 
-int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == IOMMU_MAPPING_ERROR;
-}
-
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 		phys_addr_t msi_addr, struct iommu_domain *domain)
 {
···
 		return NULL;
 
 	iova = __iommu_dma_map(dev, msi_addr, size, prot, domain);
-	if (iommu_dma_mapping_error(dev, iova))
+	if (iova == DMA_MAPPING_ERROR)
 		goto out_free_page;
 
 	INIT_LIST_HEAD(&msi_page->list);

drivers/iommu/intel-iommu.c

···
 	return 0;
 }
 
-static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
-				     size_t size, int dir, u64 dma_mask)
+static dma_addr_t __intel_map_page(struct device *dev, struct page *page,
+				   unsigned long offset, size_t size, int dir,
+				   u64 dma_mask)
 {
+	phys_addr_t paddr = page_to_phys(page) + offset;
 	struct dmar_domain *domain;
 	phys_addr_t start_paddr;
 	unsigned long iova_pfn;
···
 
 	domain = get_valid_domain_for_dev(dev);
 	if (!domain)
-		return 0;
+		return DMA_MAPPING_ERROR;
 
 	iommu = domain_get_iommu(domain);
 	size = aligned_nrpages(paddr, size);
···
 		free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
 	pr_err("Device %s request: %zx@%llx dir %d --- failed\n",
 		dev_name(dev), size, (unsigned long long)paddr, dir);
-	return 0;
+	return DMA_MAPPING_ERROR;
 }
 
 static dma_addr_t intel_map_page(struct device *dev, struct page *page,
···
 				 enum dma_data_direction dir,
 				 unsigned long attrs)
 {
-	return __intel_map_single(dev, page_to_phys(page) + offset, size,
-				  dir, *dev->dma_mask);
+	return __intel_map_page(dev, page, offset, size, dir, *dev->dma_mask);
 }
 
 static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
···
 		return NULL;
 	memset(page_address(page), 0, size);
 
-	*dma_handle = __intel_map_single(dev, page_to_phys(page), size,
-					 DMA_BIDIRECTIONAL,
-					 dev->coherent_dma_mask);
-	if (*dma_handle)
+	*dma_handle = __intel_map_page(dev, page, 0, size, DMA_BIDIRECTIONAL,
+				       dev->coherent_dma_mask);
+	if (*dma_handle != DMA_MAPPING_ERROR)
 		return page_address(page);
 	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
 		__free_pages(page, order);
···
 	return nelems;
 }
 
-static int intel_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return !dma_addr;
-}
-
 static const struct dma_map_ops intel_dma_ops = {
 	.alloc = intel_alloc_coherent,
 	.free = intel_free_coherent,
···
 	.unmap_sg = intel_unmap_sg,
 	.map_page = intel_map_page,
 	.unmap_page = intel_unmap_page,
-	.mapping_error = intel_mapping_error,
 	.dma_supported = dma_direct_supported,
 };
 

drivers/misc/mic/host/mic_boot.c

···
 	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
 	struct mic_device *mdev = scdev_to_mdev(scdev);
 	dma_addr_t tmp;
-	void *va = kmalloc(size, gfp);
+	void *va = kmalloc(size, gfp | __GFP_ZERO);
 
 	if (va) {
 		tmp = mic_map_single(mdev, va, size);

drivers/parisc/ccio-dma.c

···
 #define CMD_TLB_DIRECT_WRITE 35         /* IO_COMMAND for I/O TLB Writes     */
 #define CMD_TLB_PURGE        33         /* IO_COMMAND to Purge I/O TLB entry */
 
-#define CCIO_MAPPING_ERROR    (~(dma_addr_t)0)
-
 struct ioa_registers {
         /* Runway Supervisory Set */
         int32_t    unused1[12];
···
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
 	if (!ioc)
-		return CCIO_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	BUG_ON(size <= 0);
 
···
 	DBG_RUN_SG("%s() DONE (nents %d)\n", __func__, nents);
 }
 
-static int ccio_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == CCIO_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops ccio_ops = {
 	.dma_supported =	ccio_dma_supported,
 	.alloc =		ccio_alloc,
···
 	.unmap_page =		ccio_unmap_page,
 	.map_sg = 		ccio_map_sg,
 	.unmap_sg = 		ccio_unmap_sg,
-	.mapping_error =	ccio_mapping_error,
 };
 
 #ifdef CONFIG_PROC_FS

drivers/parisc/sba_iommu.c

···
 
 #define DEFAULT_DMA_HINT_REG	0
 
-#define SBA_MAPPING_ERROR    (~(dma_addr_t)0)
-
 struct sba_device *sba_list;
 EXPORT_SYMBOL_GPL(sba_list);
 
···
 
 	ioc = GET_IOC(dev);
 	if (!ioc)
-		return SBA_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	/* save offset bits */
 	offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK;
···
 
 }
 
-static int sba_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == SBA_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops sba_ops = {
 	.dma_supported =	sba_dma_supported,
 	.alloc =		sba_alloc,
···
 	.unmap_page =		sba_unmap_page,
 	.map_sg =		sba_map_sg,
 	.unmap_sg =		sba_unmap_sg,
-	.mapping_error =	sba_mapping_error,
 };
 
 

drivers/pci/controller/vmd.c

···
 	return &vmd->dev->dev;
 }
 
-static const struct dma_map_ops *vmd_dma_ops(struct device *dev)
-{
-	return get_dma_ops(to_vmd_dev(dev));
-}
-
 static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
 		       gfp_t flag, unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag,
-				       attrs);
+	return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
 }
 
 static void vmd_free(struct device *dev, size_t size, void *vaddr,
 		     dma_addr_t addr, unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr,
-				      attrs);
+	return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
 }
 
 static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t addr, size_t size,
 		    unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr,
-				      size, attrs);
+	return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
+			attrs);
 }
 
 static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
 			   void *cpu_addr, dma_addr_t addr, size_t size,
 			   unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr,
-					     addr, size, attrs);
+	return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
+			attrs);
 }
 
 static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
···
 			       enum dma_data_direction dir,
 			       unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size,
-					  dir, attrs);
+	return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir,
+			attrs);
 }
 
 static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
 			   enum dma_data_direction dir, unsigned long attrs)
 {
-	vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs);
+	dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs);
 }
 
 static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		      enum dma_data_direction dir, unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
+	return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
 }
 
 static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 			 enum dma_data_direction dir, unsigned long attrs)
 {
-	vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
+	dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
 }
 
 static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 				    size_t size, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
+	dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
 }
 
 static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
 				       size_t size, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size,
-						 dir);
+	dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir);
 }
 
 static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 				int nents, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
+	dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
 }
 
 static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 				   int nents, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static int vmd_mapping_error(struct device *dev, dma_addr_t addr)
-{
-	return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr);
+	dma_sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
 }
 
 static int vmd_dma_supported(struct device *dev, u64 mask)
 {
-	return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask);
+	return dma_supported(to_vmd_dev(dev), mask);
 }
 
 static u64 vmd_get_required_mask(struct device *dev)
 {
-	return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev));
+	return dma_get_required_mask(to_vmd_dev(dev));
 }
 
 static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
···
 	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device);
 	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu);
 	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device);
-	ASSIGN_VMD_DMA_OPS(source, dest, mapping_error);
 	ASSIGN_VMD_DMA_OPS(source, dest, dma_supported);
 	ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask);
 	add_dma_domain(domain);

drivers/pci/pci-driver.c

···
 		ret = of_dma_configure(dev, bridge->parent->of_node, true);
 	} else if (has_acpi_companion(bridge)) {
 		struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
-		enum dev_dma_attr attr = acpi_get_dma_attr(adev);
 
-		if (attr != DEV_DMA_NOT_SUPPORTED)
-			ret = acpi_dma_configure(dev, attr);
+		ret = acpi_dma_configure(dev, acpi_get_dma_attr(adev));
 	}
 
 	pci_put_host_bridge_device(bridge);

drivers/xen/swiotlb-xen.c

···
  * API.
  */
 
-#define XEN_SWIOTLB_ERROR_CODE	(~(dma_addr_t)0x0)
-
 static char *xen_io_tlb_start, *xen_io_tlb_end;
 static unsigned long xen_io_tlb_nslabs;
 /*
···
 
 	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir,
 				     attrs);
-	if (map == SWIOTLB_MAP_ERROR)
-		return XEN_SWIOTLB_ERROR_CODE;
+	if (map == DMA_MAPPING_ERROR)
+		return DMA_MAPPING_ERROR;
 
 	dev_addr = xen_phys_to_bus(map);
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
···
 	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
 	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
 
-	return XEN_SWIOTLB_ERROR_CODE;
+	return DMA_MAPPING_ERROR;
 }
 
 /*
···
 	xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
 
 	/* NOTE: We use dev_addr here, not paddr! */
-	if (is_xen_swiotlb_buffer(dev_addr)) {
+	if (is_xen_swiotlb_buffer(dev_addr))
 		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
-		return;
-	}
-
-	if (dir != DMA_FROM_DEVICE)
-		return;
-
-	/*
-	 * phys_to_virt doesn't work with hihgmem page but we could
-	 * call dma_mark_clean() with hihgmem page here. However, we
-	 * are fine since dma_mark_clean() is null on POWERPC. We can
-	 * make dma_mark_clean() take a physical address if necessary.
-	 */
-	dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
···
 
 	if (target == SYNC_FOR_DEVICE)
 		xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
-
-	if (dir != DMA_FROM_DEVICE)
-		return;
-
-	dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void
···
 								 sg_phys(sg),
 								 sg->length,
 								 dir, attrs);
-			if (map == SWIOTLB_MAP_ERROR) {
+			if (map == DMA_MAPPING_ERROR) {
 				dev_warn(hwdev, "swiotlb buffer is full\n");
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
···
 	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size, attrs);
 }
 
-static int xen_swiotlb_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == XEN_SWIOTLB_ERROR_CODE;
-}
-
 const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.alloc = xen_swiotlb_alloc_coherent,
 	.free = xen_swiotlb_free_coherent,
···
 	.dma_supported = xen_swiotlb_dma_supported,
 	.mmap = xen_swiotlb_dma_mmap,
 	.get_sgtable = xen_swiotlb_get_sgtable,
-	.mapping_error	= xen_swiotlb_mapping_error,
 };

include/asm-generic/dma-mapping.h

···
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return &dma_direct_ops;
+	return NULL;
 }
 
 #endif /* _ASM_GENERIC_DMA_MAPPING_H */

include/linux/dma-debug.h

···
 
 extern void dma_debug_add_bus(struct bus_type *bus);
 
-extern int dma_debug_resize_entries(u32 num_entries);
-
 extern void debug_dma_map_single(struct device *dev, const void *addr,
 				 unsigned long len);
 
···
 					     dma_addr_t dma_handle,
 					     size_t size, int direction);
 
-extern void debug_dma_sync_single_range_for_cpu(struct device *dev,
-						dma_addr_t dma_handle,
-						unsigned long offset,
-						size_t size,
-						int direction);
-
-extern void debug_dma_sync_single_range_for_device(struct device *dev,
-						   dma_addr_t dma_handle,
-						   unsigned long offset,
-						   size_t size, int direction);
-
 extern void debug_dma_sync_sg_for_cpu(struct device *dev,
 				      struct scatterlist *sg,
 				      int nelems, int direction);
···
 
 static inline void dma_debug_add_bus(struct bus_type *bus)
 {
-}
-
-static inline int dma_debug_resize_entries(u32 num_entries)
-{
-	return 0;
 }
 
 static inline void debug_dma_map_single(struct device *dev, const void *addr,
···
 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_single_range_for_cpu(struct device *dev,
-						       dma_addr_t dma_handle,
-						       unsigned long offset,
-						       size_t size,
-						       int direction)
-{
-}
-
-static inline void debug_dma_sync_single_range_for_device(struct device *dev,
-							  dma_addr_t dma_handle,
-							  unsigned long offset,
-							  size_t size,
-							  int direction)
 {
 }
 

include/linux/dma-direct.h

···
 #include <linux/dma-mapping.h>
 #include <linux/mem_encrypt.h>
 
-#define DIRECT_MAPPING_ERROR		(~(dma_addr_t)0)
-
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #else
···
 	return __sme_clr(__dma_to_phys(dev, daddr));
 }
 
-#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
-void dma_mark_clean(void *addr, size_t size);
-#else
-static inline void dma_mark_clean(void *addr, size_t size)
-{
-}
-#endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */
-
 u64 dma_direct_get_required_mask(struct device *dev);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
···
 		dma_addr_t *dma_handle, gfp_t gfp, 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);
-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);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
+struct page *__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, struct page *page);
 int dma_direct_supported(struct device *dev, u64 mask);
-int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr);
 #endif /* _LINUX_DMA_DIRECT_H */

include/linux/dma-iommu.h

···
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
-int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 /* The DMA API isn't _quite_ the whole story, though... */
 void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg);

include/linux/dma-mapping.h

···
 				   enum dma_data_direction dir);
 	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
 			enum dma_data_direction direction);
-	int (*mapping_error)(struct device *dev, dma_addr_t dma_addr);
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 };
 
-extern const struct dma_map_ops dma_direct_ops;
+#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))
 
···
 }
 #endif
 
+static inline bool dma_is_direct(const struct dma_map_ops *ops)
+{
+	return likely(!ops);
+}
+
+/*
+ * All the dma_direct_* declarations are here just for the indirect call bypass,
+ * and must not be used directly drivers!
+ */
+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);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir);
+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_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+}
+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_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+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_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir);
+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_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+}
+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_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+}
+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 dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 					      size_t size,
 					      enum dma_data_direction dir,
···
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_map_single(dev, ptr, size);
-	addr = ops->map_page(dev, virt_to_page(ptr),
-			     offset_in_page(ptr), size,
-			     dir, attrs);
+	if (dma_is_direct(ops))
+		addr = dma_direct_map_page(dev, virt_to_page(ptr),
+				offset_in_page(ptr), size, dir, attrs);
+	else
+		addr = ops->map_page(dev, virt_to_page(ptr),
+				offset_in_page(ptr), size, dir, attrs);
 	debug_dma_map_page(dev, virt_to_page(ptr),
 			   offset_in_page(ptr), size,
 			   dir, addr, true);
···
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
+	if (dma_is_direct(ops))
+		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	else if (ops->unmap_page)
 		ops->unmap_page(dev, addr, size, dir, attrs);
 	debug_dma_unmap_page(dev, addr, size, dir, true);
+}
+
+static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return dma_unmap_single_attrs(dev, addr, size, dir, attrs);
 }
 
 /*
···
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
-	ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	if (dma_is_direct(ops))
+		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
+	else
+		ents = ops->map_sg(dev, sg, nents, dir, attrs);
 	BUG_ON(ents < 0);
 	debug_dma_map_sg(dev, sg, nents, ents, dir);
 
···
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (ops->unmap_sg)
+	if (dma_is_direct(ops))
+		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
+	else if (ops->unmap_sg)
 		ops->unmap_sg(dev, sg, nents, dir, attrs);
 }
 
···
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	if (dma_is_direct(ops))
+		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	else
+		addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
 
 	return addr;
-}
-
-static inline void dma_unmap_page_attrs(struct device *dev,
-					dma_addr_t addr, size_t size,
-					enum dma_data_direction dir,
-					unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir, false);
 }
 
 static inline dma_addr_t dma_map_resource(struct device *dev,
···
 	BUG_ON(pfn_valid(PHYS_PFN(phys_addr)));
 
 	addr = phys_addr;
-	if (ops->map_resource)
+	if (ops && ops->map_resource)
 		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
 
 	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
···
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_resource)
+	if (ops && ops->unmap_resource)
 		ops->unmap_resource(dev, addr, size, dir, attrs);
 	debug_dma_unmap_resource(dev, addr, size, dir);
 }
···
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
+	if (dma_is_direct(ops))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+	else if (ops->sync_single_for_cpu)
 		ops->sync_single_for_cpu(dev, addr, size, dir);
 	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+		dma_addr_t addr, unsigned long offset, size_t size,
+		enum dma_data_direction dir)
+{
+	return dma_sync_single_for_cpu(dev, addr + offset, size, dir);
 }
 
 static inline void dma_sync_single_for_device(struct device *dev,
···
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
+	if (dma_is_direct(ops))
+		dma_direct_sync_single_for_device(dev, addr, size, dir);
+	else if (ops->sync_single_for_device)
 		ops->sync_single_for_device(dev, addr, size, dir);
 	debug_dma_sync_single_for_device(dev, addr, size, dir);
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-						 dma_addr_t addr,
-						 unsigned long offset,
-						 size_t size,
-						 enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr + offset, size, dir);
-	debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
-}
-
 static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t addr,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction dir)
+		dma_addr_t addr, unsigned long offset, size_t size,
+		enum dma_data_direction dir)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr + offset, size, dir);
-	debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
+	return dma_sync_single_for_device(dev, addr + offset, size, dir);
 }
 
 static inline void
···
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_cpu)
+	if (dma_is_direct(ops))
+		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_cpu)
 		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
 	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
 }
···
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_device)
+	if (dma_is_direct(ops))
+		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_device)
 		ops->sync_sg_for_device(dev, sg, nelems, dir);
 	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
 
···
 #define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0)
 #define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0)
 
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->cache_sync)
-		ops->cache_sync(dev, vaddr, size, dir);
-}
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction dir);
 
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
···
 			const void *caller);
 void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
 
-/**
- * dma_mmap_attrs - map a coherent DMA allocation into user space
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @vma: vm_area_struct describing requested user mapping
- * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
- * @handle: device-view address returned from dma_alloc_attrs
- * @size: size of memory originally requested in dma_alloc_attrs
- * @attrs: attributes of mapping properties requested in dma_alloc_attrs
- *
- * Map a coherent DMA buffer previously allocated by dma_alloc_attrs
- * into user space.  The coherent DMA buffer must not be freed by the
- * driver until the user space mapping has been released.
- */
-static inline int
-dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
-	       dma_addr_t dma_addr, size_t size, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	if (ops->mmap)
-		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
+int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot);
+bool dma_in_atomic_pool(void *start, size_t size);
+void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags);
+bool dma_free_from_pool(void *start, size_t size);
 
+int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
 int
 dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr,
 		dma_addr_t dma_addr, size_t size, unsigned long attrs);
 
-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)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	if (ops->get_sgtable)
-		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
-					attrs);
-	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
-			attrs);
-}
-
+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);
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 
-#ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev)	(true)
-#endif
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	void *cpu_addr;
-
-	BUG_ON(!ops);
-	WARN_ON_ONCE(dev && !dev->coherent_dma_mask);
-
-	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
-		return cpu_addr;
-
-	/* let the implementation decide on the zone to allocate from: */
-	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
-	if (!arch_dma_alloc_attrs(&dev))
-		return NULL;
-	if (!ops->alloc)
-		return NULL;
-
-	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
-	return cpu_addr;
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle,
-				     unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!ops);
-
-	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
-		return;
-	/*
-	 * On non-coherent platforms which implement DMA-coherent buffers via
-	 * non-cacheable remaps, ops->free() may call vunmap(). Thus getting
-	 * this far in IRQ context is a) at risk of a BUG_ON() or trying to
-	 * sleep on some machines, and b) an indication that the driver is
-	 * probably misusing the coherent API anyway.
-	 */
-	WARN_ON(irqs_disabled());
-
-	if (!ops->free || !cpu_addr)
-		return;
-
-	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free(dev, size, cpu_addr, dma_handle, attrs);
-}
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t flag, unsigned long attrs);
+void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_handle, unsigned long attrs);
 
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
···
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
 	debug_dma_mapping_error(dev, dma_addr);
-	if (ops->mapping_error)
-		return ops->mapping_error(dev, dma_addr);
+
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return -ENOMEM;
 	return 0;
 }
 
-static inline void dma_check_mask(struct device *dev, u64 mask)
-{
-	if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
-		dev_warn(dev, "SME is active, device will require DMA bounce buffers\n");
-}
-
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (!ops)
-		return 0;
-	if (!ops->dma_supported)
-		return 1;
-	return ops->dma_supported(dev, mask);
-}
-
-#ifndef HAVE_ARCH_DMA_SET_MASK
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	dma_check_mask(dev, mask);
-
-	*dev->dma_mask = mask;
-	return 0;
-}
-#endif
+int dma_supported(struct device *dev, u64 mask);
+int dma_set_mask(struct device *dev, u64 mask);
+int dma_set_coherent_mask(struct device *dev, u64 mask);
 
 static inline u64 dma_get_mask(struct device *dev)
 {
···
 		return *dev->dma_mask;
 	return DMA_BIT_MASK(32);
 }
-
-#ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
-int dma_set_coherent_mask(struct device *dev, u64 mask);
-#else
-static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
-{
-	if (!dma_supported(dev, mask))
-		return -EIO;
-
-	dma_check_mask(dev, mask);
-
-	dev->coherent_dma_mask = mask;
-	return 0;
-}
-#endif
 
 /*
  * Set both the DMA mask and the coherent DMA mask to the same thing.
···
 	return SZ_64K;
 }
 
-static inline unsigned int dma_set_max_seg_size(struct device *dev,
-						unsigned int size)
+static inline int dma_set_max_seg_size(struct device *dev, unsigned int size)
 {
 	if (dev->dma_parms) {
 		dev->dma_parms->max_segment_size = size;
···
 }
 #endif
 
+/*
+ * Please always use dma_alloc_coherent instead as it already zeroes the memory!
+ */
 static inline void *dma_zalloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_handle, gfp_t flag)
 {
-	void *ret = dma_alloc_coherent(dev, size, dma_handle,
-				       flag | __GFP_ZERO);
-	return ret;
+	return dma_alloc_coherent(dev, size, dma_handle, flag);
 }
 
 static inline int dma_get_cache_alignment(void)

include/linux/dma-noncoherent.h

···
 void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction);
 #else
-#define arch_dma_cache_sync NULL
+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
···
 {
 }
 #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
+void arch_dma_prep_coherent(struct page *page, size_t size);
 
 #endif /* _LINUX_DMA_NONCOHERENT_H */

include/linux/scatterlist.h

···
  * Like SG_CHUNK_SIZE, but for archs that have sg chaining. This limit
  * is totally arbitrary, a setting of 2048 will get you at least 8mb ios.
  */
-#ifdef CONFIG_ARCH_HAS_SG_CHAIN
-#define SG_MAX_SEGMENTS	2048
-#else
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
 #define SG_MAX_SEGMENTS	SG_CHUNK_SIZE
+#else
+#define SG_MAX_SEGMENTS	2048
 #endif
 
 #ifdef CONFIG_SG_POOL

include/linux/swiotlb.h

···
 	SWIOTLB_NO_FORCE,	/* swiotlb=noforce */
 };
 
-extern enum swiotlb_force swiotlb_force;
-
 /*
  * Maximum allowable number of contiguous slabs to map,
  * must be a power of 2.  What is the appropriate value ?
···
 	SYNC_FOR_DEVICE = 1,
 };
 
-/* define the last possible byte of physical address space as a mapping error */
-#define SWIOTLB_MAP_ERROR (~(phys_addr_t)0x0)
-
 extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 					  dma_addr_t tbl_dma_addr,
 					  phys_addr_t phys, size_t size,
···
 				    size_t size, enum dma_data_direction dir,
 				    enum dma_sync_target target);
 
-/* Accessory functions. */
-
-extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs);
-extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs);
-
-extern int
-swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
-		     enum dma_data_direction dir,
-		     unsigned long attrs);
-
-extern void
-swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-		       int nelems, enum dma_data_direction dir,
-		       unsigned long attrs);
-
-extern void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, enum dma_data_direction dir);
-
-extern void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			int nelems, enum dma_data_direction dir);
-
-extern void
-swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir);
-
-extern void
-swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-			   int nelems, enum dma_data_direction dir);
-
 extern int
 swiotlb_dma_supported(struct device *hwdev, u64 mask);
 
 #ifdef CONFIG_SWIOTLB
-extern void __init swiotlb_exit(void);
+extern enum swiotlb_force swiotlb_force;
+extern phys_addr_t io_tlb_start, io_tlb_end;
+
+static inline bool is_swiotlb_buffer(phys_addr_t paddr)
+{
+	return paddr >= io_tlb_start && paddr < io_tlb_end;
+}
+
+bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 #else
-static inline void swiotlb_exit(void) { }
-static inline unsigned int swiotlb_max_segment(void) { return 0; }
-#endif
+#define swiotlb_force SWIOTLB_NO_FORCE
+static inline bool is_swiotlb_buffer(phys_addr_t paddr)
+{
+	return false;
+}
+static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys,
+		dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	return false;
+}
+static inline void swiotlb_exit(void)
+{
+}
+static inline unsigned int swiotlb_max_segment(void)
+{
+	return 0;
+}
+#endif /* CONFIG_SWIOTLB */
 
 extern void swiotlb_print_info(void);
 extern void swiotlb_set_max_segment(unsigned int);
-
-extern const struct dma_map_ops swiotlb_dma_ops;
 
 #endif /* __LINUX_SWIOTLB_H */

kernel/dma/Kconfig

···
 config ARCH_HAS_DMA_MMAP_PGPROT
 	bool
 
-config DMA_DIRECT_OPS
-	bool
-	depends on HAS_DMA
-
 config DMA_NONCOHERENT_CACHE_SYNC
 	bool
-	depends on DMA_DIRECT_OPS
 
 config DMA_VIRT_OPS
 	bool
···
 
 config SWIOTLB
 	bool
-	select DMA_DIRECT_OPS
 	select NEED_DMA_MAP_STATE
+
+config DMA_REMAP
+	depends on MMU
+	bool
+
+config DMA_DIRECT_REMAP
+	bool
+	select DMA_REMAP

kernel/dma/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_HAS_DMA)			+= mapping.o
+obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o dummy.o
 obj-$(CONFIG_DMA_CMA)			+= contiguous.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o
-obj-$(CONFIG_DMA_DIRECT_OPS)		+= direct.o
 obj-$(CONFIG_DMA_VIRT_OPS)		+= virt.o
 obj-$(CONFIG_DMA_API_DEBUG)		+= debug.o
 obj-$(CONFIG_SWIOTLB)			+= swiotlb.o
-
+obj-$(CONFIG_DMA_REMAP)			+= remap.o

kernel/dma/debug.c

···
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
+#define pr_fmt(fmt)	"DMA-API: " fmt
+
 #include <linux/sched/task_stack.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
···
 #define HASH_FN_SHIFT   13
 #define HASH_FN_MASK    (HASH_SIZE - 1)
 
-/* allow architectures to override this if absolutely required */
-#ifndef PREALLOC_DMA_DEBUG_ENTRIES
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-#endif
+/* If the pool runs out, add this many new entries at once */
+#define DMA_DEBUG_DYNAMIC_ENTRIES (PAGE_SIZE / sizeof(struct dma_debug_entry))
 
 enum {
 	dma_debug_single,
···
 static struct dentry *show_num_errors_dent  __read_mostly;
 static struct dentry *num_free_entries_dent __read_mostly;
 static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *nr_total_entries_dent __read_mostly;
 static struct dentry *filter_dent           __read_mostly;
 
 /* per-driver filter related state */
···
 		error_count += 1;					\
 		if (driver_filter(dev) &&				\
 		    (show_all_errors || show_num_errors > 0)) {		\
-			WARN(1, "%s %s: " format,			\
+			WARN(1, pr_fmt("%s %s: ") format,		\
 			     dev ? dev_driver_string(dev) : "NULL",	\
 			     dev ? dev_name(dev) : "NULL", ## arg);	\
 			dump_entry_trace(entry);			\
···
 	 * prematurely.
 	 */
 	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
-		  "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
 		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
 
···
 
 	cln = to_cacheline_number(entry);
 	err_printk(entry->dev, entry,
-		   "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+		   "cpu touching an active dma mapped cacheline [cln=%pa]\n",
 		   &cln);
 }
 
···
 
 	rc = active_cacheline_insert(entry);
 	if (rc == -ENOMEM) {
-		pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
+		pr_err("cacheline tracking ENOMEM, dma-debug disabled\n");
 		global_disable = true;
 	}
 
 	/* TODO: report -EEXIST errors here as overlapping mappings are
 	 * not supported by the DMA API
 	 */
+}
+
+static int dma_debug_create_entries(gfp_t gfp)
+{
+	struct dma_debug_entry *entry;
+	int i;
+
+	entry = (void *)get_zeroed_page(gfp);
+	if (!entry)
+		return -ENOMEM;
+
+	for (i = 0; i < DMA_DEBUG_DYNAMIC_ENTRIES; i++)
+		list_add_tail(&entry[i].list, &free_entries);
+
+	num_free_entries += DMA_DEBUG_DYNAMIC_ENTRIES;
+	nr_total_entries += DMA_DEBUG_DYNAMIC_ENTRIES;
+
+	return 0;
 }
 
 static struct dma_debug_entry *__dma_entry_alloc(void)
···
 	return entry;
 }
 
+void __dma_entry_alloc_check_leak(void)
+{
+	u32 tmp = nr_total_entries % nr_prealloc_entries;
+
+	/* Shout each time we tick over some multiple of the initial pool */
+	if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) {
+		pr_info("dma_debug_entry pool grown to %u (%u00%%)\n",
+			nr_total_entries,
+			(nr_total_entries / nr_prealloc_entries));
+	}
+}
+
 /* struct dma_entry allocator
  *
  * The next two functions implement the allocator for
···
 	unsigned long flags;
 
 	spin_lock_irqsave(&free_entries_lock, flags);
-
-	if (list_empty(&free_entries)) {
-		global_disable = true;
-		spin_unlock_irqrestore(&free_entries_lock, flags);
-		pr_err("DMA-API: debugging out of memory - disabling\n");
-		return NULL;
+	if (num_free_entries == 0) {
+		if (dma_debug_create_entries(GFP_ATOMIC)) {
+			global_disable = true;
+			spin_unlock_irqrestore(&free_entries_lock, flags);
+			pr_err("debugging out of memory - disabling\n");
+			return NULL;
+		}
+		__dma_entry_alloc_check_leak();
 	}
 
 	entry = __dma_entry_alloc();
···
 	spin_unlock_irqrestore(&free_entries_lock, flags);
 }
 
-int dma_debug_resize_entries(u32 num_entries)
-{
-	int i, delta, ret = 0;
-	unsigned long flags;
-	struct dma_debug_entry *entry;
-	LIST_HEAD(tmp);
-
-	spin_lock_irqsave(&free_entries_lock, flags);
-
-	if (nr_total_entries < num_entries) {
-		delta = num_entries - nr_total_entries;
-
-		spin_unlock_irqrestore(&free_entries_lock, flags);
-
-		for (i = 0; i < delta; i++) {
-			entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-			if (!entry)
-				break;
-
-			list_add_tail(&entry->list, &tmp);
-		}
-
-		spin_lock_irqsave(&free_entries_lock, flags);
-
-		list_splice(&tmp, &free_entries);
-		nr_total_entries += i;
-		num_free_entries += i;
-	} else {
-		delta = nr_total_entries - num_entries;
-
-		for (i = 0; i < delta && !list_empty(&free_entries); i++) {
-			entry = __dma_entry_alloc();
-			kfree(entry);
-		}
-
-		nr_total_entries -= i;
-	}
-
-	if (nr_total_entries != num_entries)
-		ret = 1;
-
-	spin_unlock_irqrestore(&free_entries_lock, flags);
-
-	return ret;
-}
-
 /*
  * DMA-API debugging init code
  *
···
  *   1. Initialize core data structures
  *   2. Preallocate a given number of dma_debug_entry structs
  */
-
-static int prealloc_memory(u32 num_entries)
-{
-	struct dma_debug_entry *entry, *next_entry;
-	int i;
-
-	for (i = 0; i < num_entries; ++i) {
-		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-		if (!entry)
-			goto out_err;
-
-		list_add_tail(&entry->list, &free_entries);
-	}
-
-	num_free_entries = num_entries;
-	min_free_entries = num_entries;
-
-	pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
-
-	return 0;
-
-out_err:
-
-	list_for_each_entry_safe(entry, next_entry, &free_entries, list) {
-		list_del(&entry->list);
-		kfree(entry);
-	}
-
-	return -ENOMEM;
-}
 
 static ssize_t filter_read(struct file *file, char __user *user_buf,
 			   size_t count, loff_t *ppos)
···
 		 * switched off.
 		 */
 		if (current_driver_name[0])
-			pr_info("DMA-API: switching off dma-debug driver filter\n");
+			pr_info("switching off dma-debug driver filter\n");
 		current_driver_name[0] = 0;
 		current_driver = NULL;
 		goto out_unlock;
···
 	current_driver_name[i] = 0;
 	current_driver = NULL;
 
-	pr_info("DMA-API: enable driver filter for driver [%s]\n",
+	pr_info("enable driver filter for driver [%s]\n",
 		current_driver_name);
 
 out_unlock:
···
 {
 	dma_debug_dent = debugfs_create_dir("dma-api", NULL);
 	if (!dma_debug_dent) {
-		pr_err("DMA-API: can not create debugfs directory\n");
+		pr_err("can not create debugfs directory\n");
 		return -ENOMEM;
 	}
 
···
 			dma_debug_dent,
 			&min_free_entries);
 	if (!min_free_entries_dent)
+		goto out_err;
+
+	nr_total_entries_dent = debugfs_create_u32("nr_total_entries", 0444,
+			dma_debug_dent,
+			&nr_total_entries);
+	if (!nr_total_entries_dent)
 		goto out_err;
 
 	filter_dent = debugfs_create_file("driver_filter", 0644,
···
 		count = device_dma_allocations(dev, &entry);
 		if (count == 0)
 			break;
-		err_printk(dev, entry, "DMA-API: device driver has pending "
+		err_printk(dev, entry, "device driver has pending "
 				"DMA allocations while released from device "
 				"[count=%d]\n"
 				"One of leaked entries details: "
···
 
 static int dma_debug_init(void)
 {
-	int i;
+	int i, nr_pages;
 
 	/* Do not use dma_debug_initialized here, since we really want to be
 	 * called to set dma_debug_initialized
···
 	}
 
 	if (dma_debug_fs_init() != 0) {
-		pr_err("DMA-API: error creating debugfs entries - disabling\n");
+		pr_err("error creating debugfs entries - disabling\n");
 		global_disable = true;
 
 		return 0;
 	}
 
-	if (prealloc_memory(nr_prealloc_entries) != 0) {
-		pr_err("DMA-API: debugging out of memory error - disabled\n");
+	nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES);
+	for (i = 0; i < nr_pages; ++i)
+		dma_debug_create_entries(GFP_KERNEL);
+	if (num_free_entries >= nr_prealloc_entries) {
+		pr_info("preallocated %d debug entries\n", nr_total_entries);
+	} else if (num_free_entries > 0) {
+		pr_warn("%d debug entries requested but only %d allocated\n",
+			nr_prealloc_entries, nr_total_entries);
+	} else {
+		pr_err("debugging out of memory error - disabled\n");
 		global_disable = true;
 
 		return 0;
 	}
-
-	nr_total_entries = num_free_entries;
+	min_free_entries = num_free_entries;
 
 	dma_debug_initialized = true;
 
-	pr_info("DMA-API: debugging enabled by kernel config\n");
+	pr_info("debugging enabled by kernel config\n");
 	return 0;
 }
 core_initcall(dma_debug_init);
···
 		return -EINVAL;
 
 	if (strncmp(str, "off", 3) == 0) {
-		pr_info("DMA-API: debugging disabled on kernel command line\n");
+		pr_info("debugging disabled on kernel command line\n");
 		global_disable = true;
 	}
 
···
 
 		if (dma_mapping_error(ref->dev, ref->dev_addr)) {
 			err_printk(ref->dev, NULL,
-				   "DMA-API: device driver tries to free an "
+				   "device driver tries to free an "
 				   "invalid DMA memory address\n");
 		} else {
 			err_printk(ref->dev, NULL,
-				   "DMA-API: device driver tries to free DMA "
+				   "device driver tries to free DMA "
 				   "memory it has not allocated [device "
 				   "address=0x%016llx] [size=%llu bytes]\n",
 				   ref->dev_addr, ref->size);
···
 	}
 
 	if (ref->size != entry->size) {
-		err_printk(ref->dev, entry, "DMA-API: device driver frees "
+		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different size "
 			   "[device address=0x%016llx] [map size=%llu bytes] "
 			   "[unmap size=%llu bytes]\n",
···
 	}
 
 	if (ref->type != entry->type) {
-		err_printk(ref->dev, entry, "DMA-API: device driver frees "
+		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with wrong function "
 			   "[device address=0x%016llx] [size=%llu bytes] "
 			   "[mapped as %s] [unmapped as %s]\n",
···
 			   type2name[entry->type], type2name[ref->type]);
 	} else if ((entry->type == dma_debug_coherent) &&
 		   (phys_addr(ref) != phys_addr(entry))) {
-		err_printk(ref->dev, entry, "DMA-API: device driver frees "
+		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different CPU address "
 			   "[device address=0x%016llx] [size=%llu bytes] "
 			   "[cpu alloc address=0x%016llx] "
···
 
 	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
 	    ref->sg_call_ents != entry->sg_call_ents) {
-		err_printk(ref->dev, entry, "DMA-API: device driver frees "
+		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA sg list with different entry count "
 			   "[map count=%d] [unmap count=%d]\n",
 			   entry->sg_call_ents, ref->sg_call_ents);
···
 	 * DMA API don't handle this properly, so check for it here
 	 */
 	if (ref->direction != entry->direction) {
-		err_printk(ref->dev, entry, "DMA-API: device driver frees "
+		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different direction "
 			   "[device address=0x%016llx] [size=%llu bytes] "
 			   "[mapped with %s] [unmapped with %s]\n",
···
 	 */
 	if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
 		err_printk(ref->dev, entry,
-			   "DMA-API: device driver failed to check map error"
+			   "device driver failed to check map error"
 			   "[device address=0x%016llx] [size=%llu bytes] "
 			   "[mapped as %s]",
 			   ref->dev_addr, ref->size,
···
 			return;
 		addr = page_address(page) + offset;
 		if (object_is_on_stack(addr))
-			err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr);
+			err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr);
 	} else {
 		/* Stack is vmalloced. */
 		int i;
···
 				continue;
 
 			addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
-			err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr);
+			err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr);
 			break;
 		}
 	}
···
 {
 	if (overlap(addr, len, _stext, _etext) ||
 	    overlap(addr, len, __start_rodata, __end_rodata))
-		err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
+		err_printk(dev, NULL, "device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
 }
 
 static void check_sync(struct device *dev,
···
 	entry = bucket_find_contain(&bucket, ref, &flags);
 
 	if (!entry) {
-		err_printk(dev, NULL, "DMA-API: device driver tries "
+		err_printk(dev, NULL, "device driver tries "
 				"to sync DMA memory it has not allocated "
 				"[device address=0x%016llx] [size=%llu bytes]\n",
 				(unsigned long long)ref->dev_addr, ref->size);
···
 	}
 
 	if (ref->size > entry->size) {
-		err_printk(dev, entry, "DMA-API: device driver syncs"
+		err_printk(dev, entry, "device driver syncs"
 				" DMA memory outside allocated range "
 				"[device address=0x%016llx] "
 				"[allocation size=%llu bytes] "
···
 		goto out;
 
 	if (ref->direction != entry->direction) {
-		err_printk(dev, entry, "DMA-API: device driver syncs "
+		err_printk(dev, entry, "device driver syncs "
 				"DMA memory with different direction "
 				"[device address=0x%016llx] [size=%llu bytes] "
 				"[mapped with %s] [synced with %s]\n",
···
 
 	if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
 		      !(ref->direction == DMA_TO_DEVICE))
-		err_printk(dev, entry, "DMA-API: device driver syncs "
+		err_printk(dev, entry, "device driver syncs "
 				"device read-only DMA memory for cpu "
 				"[device address=0x%016llx] [size=%llu bytes] "
 				"[mapped with %s] [synced with %s]\n",
···
 
 	if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
 		       !(ref->direction == DMA_FROM_DEVICE))
-		err_printk(dev, entry, "DMA-API: device driver syncs "
+		err_printk(dev, entry, "device driver syncs "
 				"device write-only DMA memory to device "
 				"[device address=0x%016llx] [size=%llu bytes] "
 				"[mapped with %s] [synced with %s]\n",
···
 
 	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
 	    ref->sg_call_ents != entry->sg_call_ents) {
-		err_printk(ref->dev, entry, "DMA-API: device driver syncs "
+		err_printk(ref->dev, entry, "device driver syncs "
 			   "DMA sg list with different entry count "
 			   "[map count=%d] [sync count=%d]\n",
 			   entry->sg_call_ents, ref->sg_call_ents);
···
 	 * whoever generated the list forgot to check them.
 	 */
 	if (sg->length > max_seg)
-		err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
+		err_printk(dev, NULL, "mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
 			   sg->length, max_seg);
 	/*
 	 * In some cases this could potentially be the DMA API
···
 	start = sg_dma_address(sg);
 	end = start + sg_dma_len(sg) - 1;
 	if ((start ^ end) & ~boundary)
-		err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
+		err_printk(dev, NULL, "mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
 			   start, end, boundary);
 #endif
 }
···
 		return;
 
 	if (!virt_addr_valid(addr))
-		err_printk(dev, NULL, "DMA-API: device driver maps memory from invalid area [addr=%p] [len=%lu]\n",
+		err_printk(dev, NULL, "device driver maps memory from invalid area [addr=%p] [len=%lu]\n",
 			   addr, len);
 
 	if (is_vmalloc_addr(addr))
-		err_printk(dev, NULL, "DMA-API: device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n",
+		err_printk(dev, NULL, "device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n",
 			   addr, len);
 }
 EXPORT_SYMBOL(debug_dma_map_single);
···
 }
 EXPORT_SYMBOL(debug_dma_sync_single_for_device);
 
-void debug_dma_sync_single_range_for_cpu(struct device *dev,
-					 dma_addr_t dma_handle,
-					 unsigned long offset, size_t size,
-					 int direction)
-{
-	struct dma_debug_entry ref;
-
-	if (unlikely(dma_debug_disabled()))
-		return;
-
-	ref.type         = dma_debug_single;
-	ref.dev          = dev;
-	ref.dev_addr     = dma_handle;
-	ref.size         = offset + size;
-	ref.direction    = direction;
-	ref.sg_call_ents = 0;
-
-	check_sync(dev, &ref, true);
-}
-EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
-
-void debug_dma_sync_single_range_for_device(struct device *dev,
-					    dma_addr_t dma_handle,
-					    unsigned long offset,
-					    size_t size, int direction)
-{
-	struct dma_debug_entry ref;
-
-	if (unlikely(dma_debug_disabled()))
-		return;
-
-	ref.type         = dma_debug_single;
-	ref.dev          = dev;
-	ref.dev_addr     = dma_handle;
-	ref.size         = offset + size;
-	ref.direction    = direction;
-	ref.sg_call_ents = 0;
-
-	check_sync(dev, &ref, false);
-}
-EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
-
 void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 			       int nelems, int direction)
 {
···
 	}
 
 	if (current_driver_name[0])
-		pr_info("DMA-API: enable driver filter for driver [%s]\n",
+		pr_info("enable driver filter for driver [%s]\n",
 			current_driver_name);
 
 

kernel/dma/direct.c

···
 #include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
 #include <linux/set_memory.h>
+#include <linux/swiotlb.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but
···
 	return sev_active();
 }
 
-static bool
-check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
-		const char *caller)
+static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
-	if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
-		if (!dev->dma_mask) {
-			dev_err(dev,
-				"%s: call on device without dma_mask\n",
-				caller);
-			return false;
-		}
-
-		if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) {
-			dev_err(dev,
-				"%s: overflow %pad+%zu of device mask %llx bus mask %llx\n",
-				caller, &dma_addr, size,
-				*dev->dma_mask, dev->bus_dma_mask);
-		}
-		return false;
+	if (!dev->dma_mask) {
+		dev_err_once(dev, "DMA map on device without dma_mask\n");
+	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) {
+		dev_err_once(dev,
+			"overflow %pad+%zu of DMA mask %llx bus mask %llx\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_mask);
 	}
-	return true;
+	WARN_ON_ONCE(1);
 }
 
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
···
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask);
 }
 
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
+struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	int page_order = get_order(size);
 	struct page *page = NULL;
 	u64 phys_mask;
-	void *ret;
 
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
···
 		}
 	}
 
+	return page;
+}
+
+void *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	struct page *page;
+	void *ret;
+
+	page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
 	if (!page)
 		return NULL;
+
+	if (PageHighMem(page)) {
+		/*
+		 * Depending on the cma= arguments and per-arch setup
+		 * dma_alloc_from_contiguous could return highmem pages.
+		 * Without remapping there is no way to return them here,
+		 * so log an error and fail.
+		 */
+		dev_info(dev, "Rejecting highmem page from CMA.\n");
+		__dma_direct_free_pages(dev, size, page);
+		return NULL;
+	}
+
 	ret = page_address(page);
 	if (force_dma_unencrypted()) {
-		set_memory_decrypted((unsigned long)ret, 1 << page_order);
+		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
 		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
 	} else {
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
···
 	return ret;
 }
 
-/*
- * NOTE: this function must never look at the dma_addr argument, because we want
- * to be able to use it as a helper for iommu implementations as well.
- */
+void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(size));
+}
+
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned int page_order = get_order(size);
 
 	if (force_dma_unencrypted())
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
-	if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
-		free_pages((unsigned long)cpu_addr, page_order);
+	__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size,
···
 		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
 }
 
-static void dma_direct_sync_single_for_device(struct device *dev,
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_device(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	if (dev_is_dma_coherent(dev))
-		return;
-	arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
-}
+	phys_addr_t paddr = dma_to_phys(dev, addr);
 
-static void dma_direct_sync_sg_for_device(struct device *dev,
+	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(dev, paddr, size, dir);
+}
+EXPORT_SYMBOL(dma_direct_sync_single_for_device);
+
+void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
-		return;
+	for_each_sg(sgl, sg, nents, i) {
+		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
+					dir, SYNC_FOR_DEVICE);
 
-	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+					dir);
+	}
 }
+EXPORT_SYMBOL(dma_direct_sync_sg_for_device);
+#endif
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-static void dma_direct_sync_single_for_cpu(struct device *dev,
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	if (dev_is_dma_coherent(dev))
-		return;
-	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
-	arch_sync_dma_for_cpu_all(dev);
-}
+	phys_addr_t paddr = dma_to_phys(dev, addr);
 
-static void dma_direct_sync_sg_for_cpu(struct device *dev,
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(dev, paddr, size, dir);
+		arch_sync_dma_for_cpu_all(dev);
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL(dma_direct_sync_single_for_cpu);
+
+void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
-		return;
+	for_each_sg(sgl, sg, nents, i) {
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+	
+		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir,
+					SYNC_FOR_CPU);
+	}
 
-	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
-	arch_sync_dma_for_cpu_all(dev);
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu_all(dev);
 }
+EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
 
-static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+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);
-}
 
-static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+}
+EXPORT_SYMBOL(dma_direct_unmap_page);
+
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
+			     attrs);
 }
+EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
+
+static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
+		size_t size)
+{
+	return swiotlb_force != SWIOTLB_FORCE &&
+		(!dev || dma_capable(dev, dma_addr, size));
+}
 
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
···
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (!check_addr(dev, dma_addr, size, __func__))
-		return DIRECT_MAPPING_ERROR;
+	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
+	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
+		report_addr(dev, dma_addr, size);
+		return DMA_MAPPING_ERROR;
+	}
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_device(dev, dma_addr, size, dir);
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, phys, size, dir);
 	return dma_addr;
 }
+EXPORT_SYMBOL(dma_direct_map_page);
 
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
···
 	struct scatterlist *sg;
 
 	for_each_sg(sgl, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
-
-		sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
-		if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__))
-			return 0;
+		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
+				sg->offset, sg->length, dir, attrs);
+		if (sg->dma_address == DMA_MAPPING_ERROR)
+			goto out_unmap;
 		sg_dma_len(sg) = sg->length;
 	}
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_sg_for_device(dev, sgl, nents, dir);
 	return nents;
+
+out_unmap:
+	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+	return 0;
 }
+EXPORT_SYMBOL(dma_direct_map_sg);
 
 /*
  * Because 32-bit DMA masks are so common we expect every architecture to be
···
 	 */
 	return mask >= __phys_to_dma(dev, min_mask);
 }
-
-int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == DIRECT_MAPPING_ERROR;
-}
-
-const struct dma_map_ops dma_direct_ops = {
-	.alloc			= dma_direct_alloc,
-	.free			= dma_direct_free,
-	.map_page		= dma_direct_map_page,
-	.map_sg			= dma_direct_map_sg,
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE)
-	.sync_single_for_device	= dma_direct_sync_single_for_device,
-	.sync_sg_for_device	= dma_direct_sync_sg_for_device,
-#endif
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-	.sync_single_for_cpu	= dma_direct_sync_single_for_cpu,
-	.sync_sg_for_cpu	= dma_direct_sync_sg_for_cpu,
-	.unmap_page		= dma_direct_unmap_page,
-	.unmap_sg		= dma_direct_unmap_sg,
-#endif
-	.get_required_mask	= dma_direct_get_required_mask,
-	.dma_supported		= dma_direct_supported,
-	.mapping_error		= dma_direct_mapping_error,
-	.cache_sync		= arch_dma_cache_sync,
-};
-EXPORT_SYMBOL(dma_direct_ops);

kernel/dma/dummy.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Dummy DMA ops that always fail.
+ */
+#include <linux/dma-mapping.h>
+
+static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	return -ENXIO;
+}
+
+static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+
+static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	return 0;
+}
+
+static int dma_dummy_supported(struct device *hwdev, u64 mask)
+{
+	return 0;
+}
+
+const struct dma_map_ops dma_dummy_ops = {
+	.mmap                   = dma_dummy_mmap,
+	.map_page               = dma_dummy_map_page,
+	.map_sg                 = dma_dummy_map_sg,
+	.dma_supported          = dma_dummy_supported,
+};
+EXPORT_SYMBOL(dma_dummy_ops);

kernel/dma/mapping.c

···
  * Copyright (c) 2006  SUSE Linux Products GmbH
  * Copyright (c) 2006  Tejun Heo <[e-mail]>
  */
-
+#include <linux/memblock.h> /* for max_pfn */
 #include <linux/acpi.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
···
 		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
 	return ret;
 }
-EXPORT_SYMBOL(dma_common_get_sgtable);
+
+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)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!dma_is_direct(ops) && ops->get_sgtable)
+		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
+					attrs);
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
+			attrs);
+}
+EXPORT_SYMBOL(dma_get_sgtable_attrs);
 
 /*
  * Create userspace mapping for the DMA-coherent memory.
···
 	return -ENXIO;
 #endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
 }
-EXPORT_SYMBOL(dma_common_mmap);
 
-#ifdef CONFIG_MMU
-static struct vm_struct *__dma_common_pages_remap(struct page **pages,
-			size_t size, unsigned long vm_flags, pgprot_t prot,
-			const void *caller)
+/**
+ * dma_mmap_attrs - map a coherent DMA allocation into user space
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @vma: vm_area_struct describing requested user mapping
+ * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
+ * @dma_addr: device-view address returned from dma_alloc_attrs
+ * @size: size of memory originally requested in dma_alloc_attrs
+ * @attrs: attributes of mapping properties requested in dma_alloc_attrs
+ *
+ * Map a coherent DMA buffer previously allocated by dma_alloc_attrs into user
+ * space.  The coherent DMA buffer must not be freed by the driver until the
+ * user space mapping has been released.
+ */
+int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
 {
-	struct vm_struct *area;
+	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	area = get_vm_area_caller(size, vm_flags, caller);
-	if (!area)
-		return NULL;
+	if (!dma_is_direct(ops) && ops->mmap)
+		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+EXPORT_SYMBOL(dma_mmap_attrs);
 
-	if (map_vm_area(area, prot, pages)) {
-		vunmap(area->addr);
-		return NULL;
+#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK
+static u64 dma_default_get_required_mask(struct device *dev)
+{
+	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
+	u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
+	u64 mask;
+
+	if (!high_totalram) {
+		/* convert to mask just covering totalram */
+		low_totalram = (1 << (fls(low_totalram) - 1));
+		low_totalram += low_totalram - 1;
+		mask = low_totalram;
+	} else {
+		high_totalram = (1 << (fls(high_totalram) - 1));
+		high_totalram += high_totalram - 1;
+		mask = (((u64)high_totalram) << 32) + 0xffffffff;
 	}
-
-	return area;
+	return mask;
 }
 
-/*
- * remaps an array of PAGE_SIZE pages into another vm_area
- * Cannot be used in non-sleeping contexts
- */
-void *dma_common_pages_remap(struct page **pages, size_t size,
-			unsigned long vm_flags, pgprot_t prot,
-			const void *caller)
+u64 dma_get_required_mask(struct device *dev)
 {
-	struct vm_struct *area;
+	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-
-	return area->addr;
+	if (dma_is_direct(ops))
+		return dma_direct_get_required_mask(dev);
+	if (ops->get_required_mask)
+		return ops->get_required_mask(dev);
+	return dma_default_get_required_mask(dev);
 }
-
-/*
- * remaps an allocated contiguous region into another vm_area.
- * Cannot be used in non-sleeping contexts
- */
-
-void *dma_common_contiguous_remap(struct page *page, size_t size,
-			unsigned long vm_flags,
-			pgprot_t prot, const void *caller)
-{
-	int i;
-	struct page **pages;
-	struct vm_struct *area;
-
-	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
-	if (!pages)
-		return NULL;
-
-	for (i = 0; i < (size >> PAGE_SHIFT); i++)
-		pages[i] = nth_page(page, i);
-
-	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
-
-	kfree(pages);
-
-	if (!area)
-		return NULL;
-	return area->addr;
-}
-
-/*
- * unmaps a range previously mapped by dma_common_*_remap
- */
-void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
-{
-	struct vm_struct *area = find_vm_area(cpu_addr);
-
-	if (!area || (area->flags & vm_flags) != vm_flags) {
-		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
-		return;
-	}
-
-	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
-	vunmap(cpu_addr);
-}
+EXPORT_SYMBOL_GPL(dma_get_required_mask);
 #endif
+
+#ifndef arch_dma_alloc_attrs
+#define arch_dma_alloc_attrs(dev)	(true)
+#endif
+
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t flag, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+
+	WARN_ON_ONCE(dev && !dev->coherent_dma_mask);
+
+	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
+		return cpu_addr;
+
+	/* let the implementation decide on the zone to allocate from: */
+	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
+
+	if (!arch_dma_alloc_attrs(&dev))
+		return NULL;
+
+	if (dma_is_direct(ops))
+		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
+	else if (ops->alloc)
+		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	else
+		return NULL;
+
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
+		return;
+	/*
+	 * On non-coherent platforms which implement DMA-coherent buffers via
+	 * non-cacheable remaps, ops->free() may call vunmap(). Thus getting
+	 * this far in IRQ context is a) at risk of a BUG_ON() or trying to
+	 * sleep on some machines, and b) an indication that the driver is
+	 * probably misusing the coherent API anyway.
+	 */
+	WARN_ON(irqs_disabled());
+
+	if (!cpu_addr)
+		return;
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	if (dma_is_direct(ops))
+		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);
+	else if (ops->free)
+		ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
+EXPORT_SYMBOL(dma_free_attrs);
+
+static inline void dma_check_mask(struct device *dev, u64 mask)
+{
+	if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
+		dev_warn(dev, "SME is active, device will require DMA bounce buffers\n");
+}
+
+int dma_supported(struct device *dev, u64 mask)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_is_direct(ops))
+		return dma_direct_supported(dev, mask);
+	if (!ops->dma_supported)
+		return 1;
+	return ops->dma_supported(dev, mask);
+}
+EXPORT_SYMBOL(dma_supported);
+
+#ifndef HAVE_ARCH_DMA_SET_MASK
+int dma_set_mask(struct device *dev, u64 mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	dma_check_mask(dev, mask);
+	*dev->dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_mask);
+#endif
+
+#ifndef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (!dma_supported(dev, mask))
+		return -EIO;
+
+	dma_check_mask(dev, mask);
+	dev->coherent_dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_coherent_mask);
+#endif
+
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	if (dma_is_direct(ops))
+		arch_dma_cache_sync(dev, vaddr, size, dir);
+	else if (ops->cache_sync)
+		ops->cache_sync(dev, vaddr, size, dir);
+}
+EXPORT_SYMBOL(dma_cache_sync);

kernel/dma/remap.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (c) 2014 The Linux Foundation
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/init.h>
+#include <linux/genalloc.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+static struct vm_struct *__dma_common_pages_remap(struct page **pages,
+			size_t size, unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(size, vm_flags, caller);
+	if (!area)
+		return NULL;
+
+	if (map_vm_area(area, prot, pages)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+
+	return area;
+}
+
+/*
+ * Remaps an array of PAGE_SIZE pages into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+	if (!area)
+		return NULL;
+
+	area->pages = pages;
+
+	return area->addr;
+}
+
+/*
+ * Remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller)
+{
+	int i;
+	struct page **pages;
+	struct vm_struct *area;
+
+	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+		pages[i] = nth_page(page, i);
+
+	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+	kfree(pages);
+
+	if (!area)
+		return NULL;
+	return area->addr;
+}
+
+/*
+ * Unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || (area->flags & vm_flags) != vm_flags) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
+	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
+	vunmap(cpu_addr);
+}
+
+#ifdef CONFIG_DMA_DIRECT_REMAP
+static struct gen_pool *atomic_pool __ro_after_init;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
+static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+	atomic_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot)
+{
+	unsigned int pool_size_order = get_order(atomic_pool_size);
+	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+	struct page *page;
+	void *addr;
+	int ret;
+
+	if (dev_get_cma_area(NULL))
+		page = dma_alloc_from_contiguous(NULL, nr_pages,
+						 pool_size_order, false);
+	else
+		page = alloc_pages(gfp, pool_size_order);
+	if (!page)
+		goto out;
+
+	arch_dma_prep_coherent(page, atomic_pool_size);
+
+	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+	if (!atomic_pool)
+		goto free_page;
+
+	addr = dma_common_contiguous_remap(page, atomic_pool_size, VM_USERMAP,
+					   prot, __builtin_return_address(0));
+	if (!addr)
+		goto destroy_genpool;
+
+	ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+				page_to_phys(page), atomic_pool_size, -1);
+	if (ret)
+		goto remove_mapping;
+	gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL);
+
+	pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+		atomic_pool_size / 1024);
+	return 0;
+
+remove_mapping:
+	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+	gen_pool_destroy(atomic_pool);
+	atomic_pool = NULL;
+free_page:
+	if (!dma_release_from_contiguous(NULL, page, nr_pages))
+		__free_pages(page, pool_size_order);
+out:
+	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+		atomic_pool_size / 1024);
+	return -ENOMEM;
+}
+
+bool dma_in_atomic_pool(void *start, size_t size)
+{
+	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
+{
+	unsigned long val;
+	void *ptr = NULL;
+
+	if (!atomic_pool) {
+		WARN(1, "coherent pool not initialised!\n");
+		return NULL;
+	}
+
+	val = gen_pool_alloc(atomic_pool, size);
+	if (val) {
+		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+		*ret_page = pfn_to_page(__phys_to_pfn(phys));
+		ptr = (void *)val;
+		memset(ptr, 0, size);
+	}
+
+	return ptr;
+}
+
+bool dma_free_from_pool(void *start, size_t size)
+{
+	if (!dma_in_atomic_pool(start, size))
+		return false;
+	gen_pool_free(atomic_pool, (unsigned long)start, size);
+	return true;
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t flags, unsigned long attrs)
+{
+	struct page *page = NULL;
+	void *ret;
+
+	size = PAGE_ALIGN(size);
+
+	if (!gfpflags_allow_blocking(flags) &&
+	    !(attrs & DMA_ATTR_NO_KERNEL_MAPPING)) {
+		ret = dma_alloc_from_pool(size, &page, flags);
+		if (!ret)
+			return NULL;
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+		return ret;
+	}
+
+	page = __dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs);
+	if (!page)
+		return NULL;
+
+	/* remove any dirty cache lines on the kernel alias */
+	arch_dma_prep_coherent(page, size);
+
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
+		return page; /* opaque cookie */
+
+	/* create a coherent mapping */
+	ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
+			arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs),
+			__builtin_return_address(0));
+	if (!ret) {
+		__dma_direct_free_pages(dev, size, page);
+		return ret;
+	}
+
+	*dma_handle = phys_to_dma(dev, page_to_phys(page));
+	memset(ret, 0, size);
+
+	return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+		/* vaddr is a struct page cookie, not a kernel address */
+		__dma_direct_free_pages(dev, size, vaddr);
+	} else if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) {
+		phys_addr_t phys = dma_to_phys(dev, dma_handle);
+		struct page *page = pfn_to_page(__phys_to_pfn(phys));
+
+		vunmap(vaddr);
+		__dma_direct_free_pages(dev, size, page);
+	}
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+		dma_addr_t dma_addr)
+{
+	return __phys_to_pfn(dma_to_phys(dev, dma_addr));
+}
+#endif /* CONFIG_DMA_DIRECT_REMAP */

kernel/dma/swiotlb.c

···
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
···
  * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
-static phys_addr_t io_tlb_start, io_tlb_end;
+phys_addr_t io_tlb_start, io_tlb_end;
 
 /*
  * The number of IO TLB blocks (in groups of 64) between io_tlb_start and
···
 	max_segment = 0;
 }
 
-static int is_swiotlb_buffer(phys_addr_t paddr)
-{
-	return paddr >= io_tlb_start && paddr < io_tlb_end;
-}
-
 /*
  * Bounce: copy the swiotlb buffer back to the original dma location
  */
···
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
 		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size);
-	return SWIOTLB_MAP_ERROR;
+	return DMA_MAPPING_ERROR;
 found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 
···
 	}
 }
 
-static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys,
+/*
+ * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * to the device copy the data into it as well.
+ */
+bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t dma_addr;
+	trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
 
 	if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
 		dev_warn_ratelimited(dev,
 			"Cannot do DMA to address %pa\n", phys);
-		return DIRECT_MAPPING_ERROR;
+		return false;
 	}
 
 	/* Oh well, have to allocate and map a bounce buffer. */
 	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
 			*phys, size, dir, attrs);
-	if (*phys == SWIOTLB_MAP_ERROR)
-		return DIRECT_MAPPING_ERROR;
+	if (*phys == DMA_MAPPING_ERROR)
+		return false;
 
 	/* Ensure that the address returned is DMA'ble */
-	dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, dma_addr, size))) {
+	*dma_addr = __phys_to_dma(dev, *phys);
+	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
 		swiotlb_tbl_unmap_single(dev, *phys, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-		return DIRECT_MAPPING_ERROR;
+		return false;
 	}
 
-	return dma_addr;
-}
-
-/*
- * Map a single buffer of the indicated size for DMA in streaming mode.  The
- * physical address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
- */
-dma_addr_t swiotlb_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 dev_addr = phys_to_dma(dev, phys);
-
-	BUG_ON(dir == DMA_NONE);
-	/*
-	 * If the address happens to be in the device's DMA window,
-	 * we can safely return the device addr and not worry about bounce
-	 * buffering it.
-	 */
-	if (!dma_capable(dev, dev_addr, size) ||
-	    swiotlb_force == SWIOTLB_FORCE) {
-		trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
-		dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs);
-	}
-
-	if (!dev_is_dma_coherent(dev) &&
-	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 &&
-	    dev_addr != DIRECT_MAPPING_ERROR)
-		arch_sync_dma_for_device(dev, phys, size, dir);
-
-	return dev_addr;
-}
-
-/*
- * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_page call.  All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
-	BUG_ON(dir == DMA_NONE);
-
-	if (!dev_is_dma_coherent(hwdev) &&
-	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
-
-	if (is_swiotlb_buffer(paddr)) {
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
-		return;
-	}
-
-	if (dir != DMA_FROM_DEVICE)
-		return;
-
-	/*
-	 * phys_to_virt doesn't work with hihgmem page but we could
-	 * call dma_mark_clean() with hihgmem page here. However, we
-	 * are fine since dma_mark_clean() is null on POWERPC. We can
-	 * make dma_mark_clean() take a physical address if necessary.
-	 */
-	dma_mark_clean(phys_to_virt(paddr), size);
-}
-
-/*
- * Make physical memory consistent for a single streaming mode DMA translation
- * after a transfer.
- *
- * If you perform a swiotlb_map_page() but wish to interrogate the buffer
- * using the cpu, yet do not wish to teardown the dma mapping, you must
- * call this function before doing so.  At the next point you give the dma
- * address back to the card, you must first perform a
- * swiotlb_dma_sync_for_device, and then the device again owns the buffer
- */
-static void
-swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
-		    size_t size, enum dma_data_direction dir,
-		    enum dma_sync_target target)
-{
-	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
-	BUG_ON(dir == DMA_NONE);
-
-	if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU)
-		arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
-
-	if (is_swiotlb_buffer(paddr))
-		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
-
-	if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE)
-		arch_sync_dma_for_device(hwdev, paddr, size, dir);
-
-	if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE)
-		dma_mark_clean(phys_to_virt(paddr), size);
-}
-
-void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, enum dma_data_direction dir)
-{
-	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir)
-{
-	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
-}
-
-/*
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_page
- * interface.  Here the scatter gather list elements are each tagged with the
- * appropriate dma address and length.  They are obtained via
- * sg_dma_{address,length}(SG).
- *
- * Device ownership issues as mentioned above for swiotlb_map_page are the
- * same here.
- */
-int
-swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems,
-		     enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nelems, i) {
-		sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset,
-				sg->length, dir, attrs);
-		if (sg->dma_address == DIRECT_MAPPING_ERROR)
-			goto out_error;
-		sg_dma_len(sg) = sg->length;
-	}
-
-	return nelems;
-
-out_error:
-	swiotlb_unmap_sg_attrs(dev, sgl, i, dir,
-			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	sg_dma_len(sgl) = 0;
-	return 0;
-}
-
-/*
- * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
- */
-void
-swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-		       int nelems, enum dma_data_direction dir,
-		       unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(dir == DMA_NONE);
-
-	for_each_sg(sgl, sg, nelems, i)
-		swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir,
-			     attrs);
-}
-
-/*
- * Make physical memory consistent for a set of streaming mode DMA translations
- * after a transfer.
- *
- * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
- * and usage.
- */
-static void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
-		int nelems, enum dma_data_direction dir,
-		enum dma_sync_target target)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nelems, i)
-		swiotlb_sync_single(hwdev, sg->dma_address,
-				    sg_dma_len(sg), dir, target);
-}
-
-void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			int nelems, enum dma_data_direction dir)
-{
-	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-			   int nelems, enum dma_data_direction dir)
-{
-	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+	return true;
 }
 
 /*
···
 {
 	return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
 }
-
-const struct dma_map_ops swiotlb_dma_ops = {
-	.mapping_error		= dma_direct_mapping_error,
-	.alloc			= dma_direct_alloc,
-	.free			= dma_direct_free,
-	.sync_single_for_cpu	= swiotlb_sync_single_for_cpu,
-	.sync_single_for_device	= swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu	= swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device	= swiotlb_sync_sg_for_device,
-	.map_sg			= swiotlb_map_sg_attrs,
-	.unmap_sg		= swiotlb_unmap_sg_attrs,
-	.map_page		= swiotlb_map_page,
-	.unmap_page		= swiotlb_unmap_page,
-	.dma_supported		= dma_direct_supported,
-};
-EXPORT_SYMBOL(swiotlb_dma_ops);

kernel/dma/virt.c

···
 {
 	void *ret;
 
-	ret = (void *)__get_free_pages(gfp, get_order(size));
+	ret = (void *)__get_free_pages(gfp | __GFP_ZERO, get_order(size));
 	if (ret)
 		*dma_handle = (uintptr_t)ret;
 	return ret;

lib/Kconfig

···
 # sg chaining option
 #
 
-config ARCH_HAS_SG_CHAIN
+config ARCH_NO_SG_CHAIN
 	def_bool n
 
 config ARCH_HAS_PMEM_API

lib/scatterlist.c

···
 
 	if (nents == 0)
 		return -EINVAL;
-#ifndef CONFIG_ARCH_HAS_SG_CHAIN
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
 	if (WARN_ON_ONCE(nents > max_ents))
 		return -EINVAL;
 #endif