Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux; tag 'dma-mapping-5.5' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - improve dma-debug scalability (Eric Dumazet)

 - tiny dma-debug cleanup (Dan Carpenter)

 - check for vmap memory in dma_map_single (Kees Cook)

 - check for dma_addr_t overflows in dma-direct when using DMA offsets
   (Nicolas Saenz Julienne)

 - switch the x86 sta2x11 SOC to use more generic DMA code (Nicolas
   Saenz Julienne)

 - fix arm-nommu dma-ranges handling (Vladimir Murzin)

 - use __initdata in CMA (Shyam Saini)

 - replace the bus dma mask with a limit (Nicolas Saenz Julienne)

 - merge the remapping helpers into the main dma-direct flow (me)

 - switch xtensa to the generic dma remap handling (me)

 - various cleanups around dma_capable (me)

 - remove unused dev arguments to various dma-noncoherent helpers (me)

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux:

* tag 'dma-mapping-5.5' of git://git.infradead.org/users/hch/dma-mapping: (22 commits)
  dma-mapping: treat dev->bus_dma_mask as a DMA limit
  dma-direct: exclude dma_direct_map_resource from the min_low_pfn check
  dma-direct: don't check swiotlb=force in dma_direct_map_resource
  dma-debug: clean up put_hash_bucket()
  powerpc: remove support for NULL dev in __phys_to_dma / __dma_to_phys
  dma-direct: avoid a forward declaration for phys_to_dma
  dma-direct: unify the dma_capable definitions
  dma-mapping: drop the dev argument to arch_sync_dma_for_*
  x86/PCI: sta2x11: use default DMA address translation
  dma-direct: check for overflows on 32 bit DMA addresses
  dma-debug: increase HASH_SIZE
  dma-debug: reorder struct dma_debug_entry fields
  xtensa: use the generic uncached segment support
  dma-mapping: merge the generic remapping helpers into dma-direct
  dma-direct: provide mmap and get_sgtable method overrides
  dma-direct: remove the dma_handle argument to __dma_direct_alloc_pages
  dma-direct: remove __dma_direct_free_pages
  usb: core: Remove redundant vmap checks
  kernel: dma-contiguous: mark CMA parameters __initdata/__initconst
  dma-debug: add a schedule point in debug_dma_dump_mappings()
  ...

8 files changed, 183 insertions, 172 deletions

diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 73c5c2b8e824..4c103a24e380 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -51,9 +51,6 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
 config ARCH_HAS_DMA_PREP_COHERENT
 	bool
 
-config ARCH_HAS_DMA_COHERENT_TO_PFN
-	bool
-
 config ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	bool
 
@@ -68,9 +65,18 @@ config SWIOTLB
 	bool
 	select NEED_DMA_MAP_STATE
 
+#
+# Should be selected if we can mmap non-coherent mappings to userspace.
+# The only thing that is really required is a way to set an uncached bit
+# in the pagetables
+#
+config DMA_NONCOHERENT_MMAP
+	bool
+
 config DMA_REMAP
 	depends on MMU
 	select GENERIC_ALLOCATOR
+	select DMA_NONCOHERENT_MMAP
 	bool
 
 config DMA_DIRECT_REMAP
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 545e3869b0e3..551b0eb7028a 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -123,8 +123,9 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 	return ret;
 }
 
-static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem,
-		ssize_t size, dma_addr_t *dma_handle)
+static void *__dma_alloc_from_coherent(struct device *dev,
+				       struct dma_coherent_mem *mem,
+				       ssize_t size, dma_addr_t *dma_handle)
 {
 	int order = get_order(size);
 	unsigned long flags;
@@ -143,7 +144,7 @@ static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem,
 	/*
 	 * Memory was found in the coherent area.
 	 */
-	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+	*dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
 	ret = mem->virt_base + (pageno << PAGE_SHIFT);
 	spin_unlock_irqrestore(&mem->spinlock, flags);
 	memset(ret, 0, size);
@@ -175,17 +176,18 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
 	if (!mem)
 		return 0;
 
-	*ret = __dma_alloc_from_coherent(mem, size, dma_handle);
+	*ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle);
 	return 1;
 }
 
-void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle)
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+				     dma_addr_t *dma_handle)
 {
 	if (!dma_coherent_default_memory)
 		return NULL;
 
-	return __dma_alloc_from_coherent(dma_coherent_default_memory, size,
-			dma_handle);
+	return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size,
+					 dma_handle);
 }
 
 static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 69cfb4345388..daa4e6eefdde 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -42,10 +42,11 @@ struct cma *dma_contiguous_default_area;
  * Users, who want to set the size of global CMA area for their system
  * should use cma= kernel parameter.
  */
-static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
-static phys_addr_t size_cmdline = -1;
-static phys_addr_t base_cmdline;
-static phys_addr_t limit_cmdline;
+static const phys_addr_t size_bytes __initconst =
+	(phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+static phys_addr_t  size_cmdline __initdata = -1;
+static phys_addr_t base_cmdline __initdata;
+static phys_addr_t limit_cmdline __initdata;
 
 static int __init early_cma(char *p)
 {
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index a26170469543..2031ed1ad7fa 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -27,7 +27,7 @@
 
 #include <asm/sections.h>
 
-#define HASH_SIZE       1024ULL
+#define HASH_SIZE       16384ULL
 #define HASH_FN_SHIFT   13
 #define HASH_FN_MASK    (HASH_SIZE - 1)
 
@@ -54,40 +54,40 @@ enum map_err_types {
  * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping
  * @list: node on pre-allocated free_entries list
  * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent
- * @type: single, page, sg, coherent
- * @pfn: page frame of the start address
- * @offset: offset of mapping relative to pfn
  * @size: length of the mapping
+ * @type: single, page, sg, coherent
  * @direction: enum dma_data_direction
  * @sg_call_ents: 'nents' from dma_map_sg
  * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
+ * @pfn: page frame of the start address
+ * @offset: offset of mapping relative to pfn
  * @map_err_type: track whether dma_mapping_error() was checked
  * @stacktrace: support backtraces when a violation is detected
  */
 struct dma_debug_entry {
 	struct list_head list;
 	struct device    *dev;
-	int              type;
-	unsigned long	 pfn;
-	size_t		 offset;
 	u64              dev_addr;
 	u64              size;
+	int              type;
 	int              direction;
 	int		 sg_call_ents;
 	int		 sg_mapped_ents;
+	unsigned long	 pfn;
+	size_t		 offset;
 	enum map_err_types  map_err_type;
 #ifdef CONFIG_STACKTRACE
 	unsigned int	stack_len;
 	unsigned long	stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
 #endif
-};
+} ____cacheline_aligned_in_smp;
 
 typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
 
 struct hash_bucket {
 	struct list_head list;
 	spinlock_t lock;
-} ____cacheline_aligned_in_smp;
+};
 
 /* Hash list to save the allocated dma addresses */
 static struct hash_bucket dma_entry_hash[HASH_SIZE];
@@ -255,12 +255,10 @@ static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry,
  * Give up exclusive access to the hash bucket
  */
 static void put_hash_bucket(struct hash_bucket *bucket,
-			    unsigned long *flags)
+			    unsigned long flags)
 	__releases(&bucket->lock)
 {
-	unsigned long __flags = *flags;
-
-	spin_unlock_irqrestore(&bucket->lock, __flags);
+	spin_unlock_irqrestore(&bucket->lock, flags);
 }
 
 static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
@@ -359,7 +357,7 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 		/*
 		 * Nothing found, go back a hash bucket
 		 */
-		put_hash_bucket(*bucket, flags);
+		put_hash_bucket(*bucket, *flags);
 		range          += (1 << HASH_FN_SHIFT);
 		index.dev_addr -= (1 << HASH_FN_SHIFT);
 		*bucket = get_hash_bucket(&index, flags);
@@ -420,6 +418,7 @@ void debug_dma_dump_mappings(struct device *dev)
 		}
 
 		spin_unlock_irqrestore(&bucket->lock, flags);
+		cond_resched();
 	}
 }
 
@@ -608,7 +607,7 @@ static void add_dma_entry(struct dma_debug_entry *entry)
 
 	bucket = get_hash_bucket(entry, &flags);
 	hash_bucket_add(bucket, entry);
-	put_hash_bucket(bucket, &flags);
+	put_hash_bucket(bucket, flags);
 
 	rc = active_cacheline_insert(entry);
 	if (rc == -ENOMEM) {
@@ -1001,7 +1000,7 @@ static void check_unmap(struct dma_debug_entry *ref)
 
 	if (!entry) {
 		/* must drop lock before calling dma_mapping_error */
-		put_hash_bucket(bucket, &flags);
+		put_hash_bucket(bucket, flags);
 
 		if (dma_mapping_error(ref->dev, ref->dev_addr)) {
 			err_printk(ref->dev, NULL,
@@ -1083,7 +1082,7 @@ static void check_unmap(struct dma_debug_entry *ref)
 	hash_bucket_del(entry);
 	dma_entry_free(entry);
 
-	put_hash_bucket(bucket, &flags);
+	put_hash_bucket(bucket, flags);
 }
 
 static void check_for_stack(struct device *dev,
@@ -1203,7 +1202,7 @@ static void check_sync(struct device *dev,
 	}
 
 out:
-	put_hash_bucket(bucket, &flags);
+	put_hash_bucket(bucket, flags);
 }
 
 static void check_sg_segment(struct device *dev, struct scatterlist *sg)
@@ -1318,7 +1317,7 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 		}
 	}
 
-	put_hash_bucket(bucket, &flags);
+	put_hash_bucket(bucket, flags);
 }
 EXPORT_SYMBOL(debug_dma_mapping_error);
 
@@ -1391,7 +1390,7 @@ static int get_nr_mapped_entries(struct device *dev,
 
 	if (entry)
 		mapped_ents = entry->sg_mapped_ents;
-	put_hash_bucket(bucket, &flags);
+	put_hash_bucket(bucket, flags);
 
 	return mapped_ents;
 }
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 0b67c04e531b..6af7ae83c4ad 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -12,6 +12,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
+#include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/swiotlb.h>
 
@@ -26,10 +27,10 @@ static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
 	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) {
+	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) {
 		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);
+			"overflow %pad+%zu of DMA mask %llx bus limit %llx\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
 	}
 	WARN_ON_ONCE(1);
 }
@@ -42,6 +43,12 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 	return phys_to_dma(dev, phys);
 }
 
+static inline struct page *dma_direct_to_page(struct device *dev,
+		dma_addr_t dma_addr)
+{
+	return pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_addr)));
+}
+
 u64 dma_direct_get_required_mask(struct device *dev)
 {
 	u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
@@ -50,15 +57,14 @@ u64 dma_direct_get_required_mask(struct device *dev)
 }
 
 static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-		u64 *phys_mask)
+		u64 *phys_limit)
 {
-	if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask)
-		dma_mask = dev->bus_dma_mask;
+	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
 	if (force_dma_unencrypted(dev))
-		*phys_mask = __dma_to_phys(dev, dma_mask);
+		*phys_limit = __dma_to_phys(dev, dma_limit);
 	else
-		*phys_mask = dma_to_phys(dev, dma_mask);
+		*phys_limit = dma_to_phys(dev, dma_limit);
 
 	/*
 	 * Optimistically try the zone that the physical address mask falls
@@ -68,9 +74,9 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
-	if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits))
+	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
-	if (*phys_mask <= DMA_BIT_MASK(32))
+	if (*phys_limit <= DMA_BIT_MASK(32))
 		return GFP_DMA32;
 	return 0;
 }
@@ -78,16 +84,16 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask);
+			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+		gfp_t gfp, unsigned long attrs)
 {
 	size_t alloc_size = PAGE_ALIGN(size);
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
-	u64 phys_mask;
+	u64 phys_limit;
 
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
@@ -95,7 +101,7 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	/* we always manually zero the memory once we are done: */
 	gfp &= ~__GFP_ZERO;
 	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-			&phys_mask);
+			&phys_limit);
 	page = dma_alloc_contiguous(dev, alloc_size, gfp);
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		dma_free_contiguous(dev, page, alloc_size);
@@ -109,7 +115,7 @@ again:
 		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
-		    phys_mask < DMA_BIT_MASK(64) &&
+		    phys_limit < DMA_BIT_MASK(64) &&
 		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
 			gfp |= GFP_DMA32;
 			goto again;
@@ -130,7 +136,16 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	struct page *page;
 	void *ret;
 
-	page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_alloc_need_uncached(dev, attrs) &&
+	    !gfpflags_allow_blocking(gfp)) {
+		ret = dma_alloc_from_pool(PAGE_ALIGN(size), &page, gfp);
+		if (!ret)
+			return NULL;
+		goto done;
+	}
+
+	page = __dma_direct_alloc_pages(dev, size, gfp, attrs);
 	if (!page)
 		return NULL;
 
@@ -139,9 +154,28 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		/* remove any dirty cache lines on the kernel alias */
 		if (!PageHighMem(page))
 			arch_dma_prep_coherent(page, size);
-		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 		/* return the page pointer as the opaque cookie */
-		return page;
+		ret = page;
+		goto done;
+	}
+
+	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	     dma_alloc_need_uncached(dev, attrs)) ||
+	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
+		/* remove any dirty cache lines on the kernel alias */
+		arch_dma_prep_coherent(page, PAGE_ALIGN(size));
+
+		/* create a coherent mapping */
+		ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size),
+				dma_pgprot(dev, PAGE_KERNEL, attrs),
+				__builtin_return_address(0));
+		if (!ret) {
+			dma_free_contiguous(dev, page, size);
+			return ret;
+		}
+
+		memset(ret, 0, size);
+		goto done;
 	}
 
 	if (PageHighMem(page)) {
@@ -152,17 +186,14 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		 * so log an error and fail.
 		 */
 		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		__dma_direct_free_pages(dev, size, page);
+		dma_free_contiguous(dev, page, size);
 		return NULL;
 	}
 
 	ret = page_address(page);
-	if (force_dma_unencrypted(dev)) {
+	if (force_dma_unencrypted(dev))
 		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));
-	}
+
 	memset(ret, 0, size);
 
 	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
@@ -170,15 +201,14 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		arch_dma_prep_coherent(page, size);
 		ret = uncached_kernel_address(ret);
 	}
-
+done:
+	if (force_dma_unencrypted(dev))
+		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
+	else
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 	return ret;
 }
 
-void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
-{
-	dma_free_contiguous(dev, page, size);
-}
-
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
@@ -187,23 +217,28 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
 		/* cpu_addr is a struct page cookie, not a kernel address */
-		__dma_direct_free_pages(dev, size, cpu_addr);
+		dma_free_contiguous(dev, cpu_addr, size);
 		return;
 	}
 
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_free_from_pool(cpu_addr, PAGE_ALIGN(size)))
+		return;
+
 	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		cpu_addr = cached_kernel_address(cpu_addr);
-	__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
+		vunmap(cpu_addr);
+
+	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
 	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
@@ -213,6 +248,7 @@ void dma_direct_free(struct device *dev, size_t size,
 		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
 	else
@@ -230,7 +266,7 @@ void dma_direct_sync_single_for_device(struct device *dev,
 		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);
+		arch_sync_dma_for_device(paddr, size, dir);
 }
 EXPORT_SYMBOL(dma_direct_sync_single_for_device);
 
@@ -248,7 +284,7 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 					dir, SYNC_FOR_DEVICE);
 
 		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_device(dev, paddr, sg->length,
+			arch_sync_dma_for_device(paddr, sg->length,
 					dir);
 	}
 }
@@ -264,8 +300,8 @@ void dma_direct_sync_single_for_cpu(struct device *dev,
 	phys_addr_t paddr = dma_to_phys(dev, addr);
 
 	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(dev, paddr, size, dir);
-		arch_sync_dma_for_cpu_all(dev);
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
 	}
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
@@ -283,7 +319,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
 
 		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_cpu(dev, paddr, sg->length, dir);
+			arch_sync_dma_for_cpu(paddr, sg->length, dir);
 
 		if (unlikely(is_swiotlb_buffer(paddr)))
 			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
@@ -291,7 +327,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 	}
 
 	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_cpu_all(dev);
+		arch_sync_dma_for_cpu_all();
 }
 EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
 
@@ -325,7 +361,7 @@ static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
 		size_t size)
 {
 	return swiotlb_force != SWIOTLB_FORCE &&
-		dma_capable(dev, dma_addr, size);
+		dma_capable(dev, dma_addr, size, true);
 }
 
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
@@ -342,7 +378,7 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	}
 
 	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return dma_addr;
 }
 EXPORT_SYMBOL(dma_direct_map_page);
@@ -374,7 +410,7 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 {
 	dma_addr_t dma_addr = paddr;
 
-	if (unlikely(!dma_direct_possible(dev, dma_addr, size))) {
+	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
 		report_addr(dev, dma_addr, size);
 		return DMA_MAPPING_ERROR;
 	}
@@ -383,6 +419,59 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 }
 EXPORT_SYMBOL(dma_direct_map_resource);
 
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	struct page *page = dma_direct_to_page(dev, dma_addr);
+	int ret;
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (!ret)
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return ret;
+}
+
+#ifdef CONFIG_MMU
+bool dma_direct_can_mmap(struct device *dev)
+{
+	return dev_is_dma_coherent(dev) ||
+		IS_ENABLED(CONFIG_DMA_NONCOHERENT_MMAP);
+}
+
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr));
+	int ret = -ENXIO;
+
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff)
+		return -ENXIO;
+	return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
+			user_count << PAGE_SHIFT, vma->vm_page_prot);
+}
+#else /* CONFIG_MMU */
+bool dma_direct_can_mmap(struct device *dev)
+{
+	return false;
+}
+
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	return -ENXIO;
+}
+#endif /* CONFIG_MMU */
+
 /*
  * Because 32-bit DMA masks are so common we expect every architecture to be
  * able to satisfy them - either by not supporting more physical memory, or by
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index d9334f31a5af..12ff766ec1fa 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -112,24 +112,9 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		 unsigned long attrs)
 {
-	struct page *page;
+	struct page *page = virt_to_page(cpu_addr);
 	int ret;
 
-	if (!dev_is_dma_coherent(dev)) {
-		unsigned long pfn;
-
-		if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
-			return -ENXIO;
-
-		/* If the PFN is not valid, we do not have a struct page */
-		pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
-		if (!pfn_valid(pfn))
-			return -ENXIO;
-		page = pfn_to_page(pfn);
-	} else {
-		page = virt_to_page(cpu_addr);
-	}
-
 	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 	if (!ret)
 		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
@@ -154,7 +139,7 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	if (dma_is_direct(ops))
-		return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr,
+		return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
 				size, attrs);
 	if (!ops->get_sgtable)
 		return -ENXIO;
@@ -192,7 +177,6 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
-	unsigned long pfn;
 	int ret = -ENXIO;
 
 	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
@@ -203,19 +187,8 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	if (off >= count || user_count > count - off)
 		return -ENXIO;
 
-	if (!dev_is_dma_coherent(dev)) {
-		if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
-			return -ENXIO;
-
-		/* If the PFN is not valid, we do not have a struct page */
-		pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
-		if (!pfn_valid(pfn))
-			return -ENXIO;
-	} else {
-		pfn = page_to_pfn(virt_to_page(cpu_addr));
-	}
-
-	return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
+	return remap_pfn_range(vma, vma->vm_start,
+			page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
 			user_count << PAGE_SHIFT, vma->vm_page_prot);
 #else
 	return -ENXIO;
@@ -233,12 +206,8 @@ bool dma_can_mmap(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops)) {
-		return IS_ENABLED(CONFIG_MMU) &&
-		       (dev_is_dma_coherent(dev) ||
-			IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN));
-	}
-
+	if (dma_is_direct(ops))
+		return dma_direct_can_mmap(dev);
 	return ops->mmap != NULL;
 }
 EXPORT_SYMBOL_GPL(dma_can_mmap);
@@ -263,7 +232,7 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	if (dma_is_direct(ops))
-		return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size,
+		return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
 				attrs);
 	if (!ops->mmap)
 		return -ENXIO;
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index c00b9258fa6a..d47bd40fc0f5 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -210,59 +210,4 @@ bool dma_free_from_pool(void *start, size_t size)
 	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)) {
-		ret = dma_alloc_from_pool(size, &page, flags);
-		if (!ret)
-			return NULL;
-		goto done;
-	}
-
-	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);
-
-	/* create a coherent mapping */
-	ret = dma_common_contiguous_remap(page, size,
-			dma_pgprot(dev, PAGE_KERNEL, attrs),
-			__builtin_return_address(0));
-	if (!ret) {
-		__dma_direct_free_pages(dev, size, page);
-		return ret;
-	}
-
-	memset(ret, 0, size);
-done:
-	*dma_handle = phys_to_dma(dev, page_to_phys(page));
-	return ret;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	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 */
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 673a2cdb2656..9280d6f8271e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -678,7 +678,7 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 
 	/* Ensure that the address returned is DMA'ble */
 	*dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
+	if (unlikely(!dma_capable(dev, *dma_addr, size, true))) {
 		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return false;