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
  ...

8 files changed, 186 insertions, 310 deletions

diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h
index 880a292d792f..c13f46109e88 100644
--- a/include/asm-generic/dma-mapping.h
+++ b/include/asm-generic/dma-mapping.h
@@ -4,7 +4,7 @@
 
 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 */
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index 30213adbb6b9..2ad5c363d7d5 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -30,8 +30,6 @@ struct bus_type;
 
 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);
 
@@ -72,17 +70,6 @@ extern void debug_dma_sync_single_for_device(struct device *dev,
 					     dma_addr_t dma_handle,
 					     size_t size, int direction);
 
-extern void debug_dma_sync_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);
@@ -101,11 +88,6 @@ 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,
 					unsigned long len)
 {
@@ -174,22 +156,6 @@ static inline void debug_dma_sync_single_for_device(struct device *dev,
 {
 }
 
-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)
-{
-}
-
 static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
 					     struct scatterlist *sg,
 					     int nelems, int direction)
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 9e66bfe369aa..b7338702592a 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -5,8 +5,6 @@
 #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
@@ -50,14 +48,6 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 	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);
@@ -67,11 +57,8 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
-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 */
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index e8ca5e654277..e760dc5d1fa8 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -69,7 +69,6 @@ dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		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);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index d327bdd53716..ba521d5506c9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -128,13 +128,14 @@ struct dma_map_ops {
 				   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))
 
@@ -220,6 +221,69 @@ static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 }
 #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,
@@ -230,9 +294,12 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 
 	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);
@@ -247,11 +314,19 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
 	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);
+}
+
 /*
  * dma_maps_sg_attrs returns 0 on error and > 0 on success.
  * It should never return a value < 0.
@@ -264,7 +339,10 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 	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);
 
@@ -279,7 +357,9 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg
 
 	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);
 }
 
@@ -293,25 +373,15 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 	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,
 					  phys_addr_t phys_addr,
 					  size_t size,
@@ -327,7 +397,7 @@ 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);
@@ -342,7 +412,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t 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);
 }
@@ -354,11 +424,20 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 	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,
 					      dma_addr_t addr, size_t size,
 					      enum dma_data_direction dir)
@@ -366,37 +445,18 @@ 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
@@ -406,7 +466,9 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 	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);
 }
@@ -418,7 +480,9 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	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);
 
@@ -431,16 +495,8 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 #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,
@@ -455,107 +511,29 @@ void *dma_common_pages_remap(struct page **pages, 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)
@@ -573,43 +551,16 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 
 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);
-	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;
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return -ENOMEM;
 	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)
 {
@@ -618,21 +569,6 @@ static inline u64 dma_get_mask(struct device *dev)
 	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.
  * Note that we don't check the return value from dma_set_coherent_mask()
@@ -676,8 +612,7 @@ static inline unsigned int dma_get_max_seg_size(struct device *dev)
 	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;
@@ -709,12 +644,13 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 }
 #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)
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 9051b055beec..69b36ed31a99 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -38,7 +38,10 @@ pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
 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
@@ -69,4 +72,6 @@ static inline void arch_sync_dma_for_cpu_all(struct device *dev)
 }
 #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 */
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 093aa57120b0..b96f0d0b5b8f 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -324,10 +324,10 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
  * 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
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index a387b59640a4..7c007ed7505f 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -16,8 +16,6 @@ enum swiotlb_force {
 	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 ?
@@ -46,9 +44,6 @@ enum dma_sync_target {
 	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,
@@ -65,56 +60,44 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev,
 				    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 */