Merge tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - convert arm32 to the common dma-direct code (Arnd Bergmann, Robin
   Murphy, Christoph Hellwig)

 - restructure the PCIe peer to peer mapping support (Logan Gunthorpe)

 - allow the IOMMU code to communicate an optional DMA mapping length
   and use that in scsi and libata (John Garry)

 - split the global swiotlb lock (Tianyu Lan)

 - various fixes and cleanup (Chao Gao, Dan Carpenter, Dongli Zhang,
   Lukas Bulwahn, Robin Murphy)

* tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping: (45 commits)
  swiotlb: fix passing local variable to debugfs_create_ulong()
  dma-mapping: reformat comment to suppress htmldoc warning
  PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg()
  RDMA/rw: drop pci_p2pdma_[un]map_sg()
  RDMA/core: introduce ib_dma_pci_p2p_dma_supported()
  nvme-pci: convert to using dma_map_sgtable()
  nvme-pci: check DMA ops when indicating support for PCI P2PDMA
  iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg
  iommu: Explicitly skip bus address marked segments in __iommu_map_sg()
  dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support
  dma-direct: support PCI P2PDMA pages in dma-direct map_sg
  dma-mapping: allow EREMOTEIO return code for P2PDMA transfers
  PCI/P2PDMA: Introduce helpers for dma_map_sg implementations
  PCI/P2PDMA: Attempt to set map_type if it has not been set
  lib/scatterlist: add flag for indicating P2PDMA segments in an SGL
  swiotlb: clean up some coding style and minor issues
  dma-mapping: update comment after dmabounce removal
  scsi: sd: Add a comment about limiting max_sectors to shost optimal limit
  ata: libata-scsi: cap ata_device->max_sectors according to shost->max_sectors
  scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit
  ...

1 files changed, 73 insertions, 579 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1483b6a4319d..089c9c644cce 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -103,139 +103,6 @@ static struct arm_dma_buffer *arm_dma_buffer_find(void *virt)
  * before transfers and delay cache invalidation until transfer completion.
  *
  */
-static void __dma_page_cpu_to_dev(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-static void __dma_page_dev_to_cpu(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-
-/**
- * arm_dma_map_page - map a portion of a page for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_page().
- */
-static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__dma_page_cpu_to_dev(page, offset, size, dir);
-	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
-}
-
-static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
-{
-	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
-}
-
-/**
- * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_page)
- * @dir: DMA transfer direction (same as passed to dma_map_page)
- *
- * Unmap a page streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_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.
- */
-static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
-				      handle & ~PAGE_MASK, size, dir);
-}
-
-static void arm_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned int offset = handle & (PAGE_SIZE - 1);
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
-	__dma_page_dev_to_cpu(page, offset, size, dir);
-}
-
-static void arm_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned int offset = handle & (PAGE_SIZE - 1);
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
-	__dma_page_cpu_to_dev(page, offset, size, dir);
-}
-
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- */
-static int arm_dma_supported(struct device *dev, u64 mask)
-{
-	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
-
-	/*
-	 * Translate the device's DMA mask to a PFN limit.  This
-	 * PFN number includes the page which we can DMA to.
-	 */
-	return dma_to_pfn(dev, mask) >= max_dma_pfn;
-}
-
-const struct dma_map_ops arm_dma_ops = {
-	.alloc			= arm_dma_alloc,
-	.free			= arm_dma_free,
-	.alloc_pages		= dma_direct_alloc_pages,
-	.free_pages		= dma_direct_free_pages,
-	.mmap			= arm_dma_mmap,
-	.get_sgtable		= arm_dma_get_sgtable,
-	.map_page		= arm_dma_map_page,
-	.unmap_page		= arm_dma_unmap_page,
-	.map_sg			= arm_dma_map_sg,
-	.unmap_sg		= arm_dma_unmap_sg,
-	.map_resource		= dma_direct_map_resource,
-	.sync_single_for_cpu	= arm_dma_sync_single_for_cpu,
-	.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,
-	.dma_supported		= arm_dma_supported,
-	.get_required_mask	= dma_direct_get_required_mask,
-};
-EXPORT_SYMBOL(arm_dma_ops);
-
-static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
-	dma_addr_t *handle, gfp_t gfp, unsigned long attrs);
-static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
-				  dma_addr_t handle, unsigned long attrs);
-static int arm_coherent_dma_mmap(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 arm_coherent_dma_ops = {
-	.alloc			= arm_coherent_dma_alloc,
-	.free			= arm_coherent_dma_free,
-	.alloc_pages		= dma_direct_alloc_pages,
-	.free_pages		= dma_direct_free_pages,
-	.mmap			= arm_coherent_dma_mmap,
-	.get_sgtable		= arm_dma_get_sgtable,
-	.map_page		= arm_coherent_dma_map_page,
-	.map_sg			= arm_dma_map_sg,
-	.map_resource		= dma_direct_map_resource,
-	.dma_supported		= arm_dma_supported,
-	.get_required_mask	= dma_direct_get_required_mask,
-};
-EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
@@ -725,7 +592,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	if (page) {
 		unsigned long flags;
 
-		*handle = pfn_to_dma(dev, page_to_pfn(page));
+		*handle = phys_to_dma(dev, page_to_phys(page));
 		buf->virt = args.want_vaddr ? addr : page;
 
 		spin_lock_irqsave(&arm_dma_bufs_lock, flags);
@@ -739,74 +606,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 }
 
 /*
- * Allocate DMA-coherent memory space and return both the kernel remapped
- * virtual and bus address for that space.
- */
-void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-		    gfp_t gfp, unsigned long attrs)
-{
-	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
-
-	return __dma_alloc(dev, size, handle, gfp, prot, false,
-			   attrs, __builtin_return_address(0));
-}
-
-static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
-	dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true,
-			   attrs, __builtin_return_address(0));
-}
-
-static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	int ret = -ENXIO;
-	unsigned long nr_vma_pages = vma_pages(vma);
-	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long pfn = dma_to_pfn(dev, dma_addr);
-	unsigned long off = vma->vm_pgoff;
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      vma->vm_end - vma->vm_start,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-
-/*
- * Create userspace mapping for the DMA-coherent memory.
- */
-static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-/*
  * Free a buffer as defined by the above mapping.
  */
 static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 			   dma_addr_t handle, unsigned long attrs,
 			   bool is_coherent)
 {
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	struct page *page = phys_to_page(dma_to_phys(dev, handle));
 	struct arm_dma_buffer *buf;
 	struct arm_dma_free_args args = {
 		.dev = dev,
@@ -824,40 +630,6 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 	kfree(buf);
 }
 
-void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		  dma_addr_t handle, unsigned long attrs)
-{
-	__arm_dma_free(dev, size, cpu_addr, handle, attrs, false);
-}
-
-static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
-				  dma_addr_t handle, unsigned long attrs)
-{
-	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
-}
-
-int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-		 void *cpu_addr, dma_addr_t handle, size_t size,
-		 unsigned long attrs)
-{
-	unsigned long pfn = dma_to_pfn(dev, handle);
-	struct page *page;
-	int ret;
-
-	/* If the PFN is not valid, we do not have a struct page */
-	if (!pfn_valid(pfn))
-		return -ENXIO;
-
-	page = pfn_to_page(pfn);
-
-	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-	if (unlikely(ret))
-		return ret;
-
-	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
-	return 0;
-}
-
 static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
@@ -907,8 +679,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 
 /*
  * Make an area consistent for devices.
- * Note: Drivers should NOT use this function directly, as it will break
- * platforms with CONFIG_DMABOUNCE.
+ * Note: Drivers should NOT use this function directly.
  * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
  */
 static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
@@ -961,122 +732,6 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	}
 }
 
-/**
- * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the dma_map_single 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}.
- *
- * Device ownership issues as mentioned for dma_map_single are the same
- * here.
- */
-int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-	int i, j, ret;
-
-	for_each_sg(sg, s, nents, i) {
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		s->dma_length = s->length;
-#endif
-		s->dma_address = ops->map_page(dev, sg_page(s), s->offset,
-						s->length, dir, attrs);
-		if (dma_mapping_error(dev, s->dma_address)) {
-			ret = -EIO;
-			goto bad_mapping;
-		}
-	}
-	return nents;
-
- bad_mapping:
-	for_each_sg(sg, s, i, j)
-		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
-	return ret;
-}
-
-/**
- * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- *
- * Unmap a set of streaming mode DMA translations.  Again, CPU access
- * rules concerning calls here are the same as for dma_unmap_single().
- */
-void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
-}
-
-/**
- * arm_dma_sync_sg_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map (returned from dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- */
-void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length,
-					 dir);
-}
-
-/**
- * arm_dma_sync_sg_for_device
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map (returned from dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- */
-void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		ops->sync_single_for_device(dev, sg_dma_address(s), s->length,
-					    dir);
-}
-
-static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
-{
-	/*
-	 * When CONFIG_ARM_LPAE is set, physical address can extend above
-	 * 32-bits, which then can't be addressed by devices that only support
-	 * 32-bit DMA.
-	 * Use the generic dma-direct / swiotlb ops code in that case, as that
-	 * handles bounce buffering for us.
-	 */
-	if (IS_ENABLED(CONFIG_ARM_LPAE))
-		return NULL;
-	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
-}
-
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
 static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
@@ -1423,13 +1078,13 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
 		__free_from_pool(cpu_addr, size);
 }
 
-static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
-	    dma_addr_t *handle, gfp_t gfp, unsigned long attrs,
-	    int coherent_flag)
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+	    dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
 {
 	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	struct page **pages;
 	void *addr = NULL;
+	int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL;
 
 	*handle = DMA_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
@@ -1472,19 +1127,7 @@ err_buffer:
 	return NULL;
 }
 
-static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
-	    dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL);
-}
-
-static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size,
-		    dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT);
-}
-
-static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    unsigned long attrs)
 {
@@ -1498,35 +1141,24 @@ static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma
 	if (vma->vm_pgoff >= nr_pages)
 		return -ENXIO;
 
+	if (!dev->dma_coherent)
+		vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
 	err = vm_map_pages(vma, pages, nr_pages);
 	if (err)
 		pr_err("Remapping memory failed: %d\n", err);
 
 	return err;
 }
-static int arm_iommu_mmap_attrs(struct device *dev,
-		struct vm_area_struct *vma, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs)
-{
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
-	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-static int arm_coherent_iommu_mmap_attrs(struct device *dev,
-		struct vm_area_struct *vma, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs)
-{
-	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
 
 /*
  * free a page as defined by the above mapping.
  * Must not be called with IRQs disabled.
  */
-static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-	dma_addr_t handle, unsigned long attrs, int coherent_flag)
+static void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+	dma_addr_t handle, unsigned long attrs)
 {
+	int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL;
 	struct page **pages;
 	size = PAGE_ALIGN(size);
 
@@ -1548,19 +1180,6 @@ static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_ad
 	__iommu_free_buffer(dev, pages, size, attrs);
 }
 
-static void arm_iommu_free_attrs(struct device *dev, size_t size,
-				 void *cpu_addr, dma_addr_t handle,
-				 unsigned long attrs)
-{
-	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL);
-}
-
-static void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
-		    void *cpu_addr, dma_addr_t handle, unsigned long attrs)
-{
-	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT);
-}
-
 static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 				 void *cpu_addr, dma_addr_t dma_addr,
 				 size_t size, unsigned long attrs)
@@ -1580,8 +1199,7 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
  */
 static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			  size_t size, dma_addr_t *handle,
-			  enum dma_data_direction dir, unsigned long attrs,
-			  bool is_coherent)
+			  enum dma_data_direction dir, unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova, iova_base;
@@ -1601,7 +1219,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		phys_addr_t phys = page_to_phys(sg_page(s));
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
-		if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
 		prot = __dma_info_to_prot(dir, attrs);
@@ -1621,9 +1239,20 @@ fail:
 	return ret;
 }
 
-static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		     enum dma_data_direction dir, unsigned long attrs,
-		     bool is_coherent)
+/**
+ * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map
+ * @dir: DMA transfer direction
+ *
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * The scatter gather list elements are merged together (if possible) and
+ * tagged with the appropriate dma address and length. They are obtained via
+ * sg_dma_{address,length}.
+ */
+static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *s = sg, *dma = sg, *start = sg;
 	int i, count = 0, ret;
@@ -1638,8 +1267,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
 			ret = __map_sg_chunk(dev, start, size,
-					     &dma->dma_address, dir, attrs,
-					     is_coherent);
+					     &dma->dma_address, dir, attrs);
 			if (ret < 0)
 				goto bad_mapping;
 
@@ -1653,8 +1281,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		}
 		size += s->length;
 	}
-	ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs,
-			     is_coherent);
+	ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs);
 	if (ret < 0)
 		goto bad_mapping;
 
@@ -1672,44 +1299,19 @@ bad_mapping:
 }
 
 /**
- * arm_coherent_iommu_map_sg - map a set of SG buffers for streaming mode DMA
- * @dev: valid struct device pointer
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Map a set of i/o coherent buffers described by scatterlist in streaming
- * mode for DMA. The scatter gather list elements are merged together (if
- * possible) and tagged with the appropriate dma address and length. They are
- * obtained via sg_dma_{address,length}.
- */
-static int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_map_sg(dev, sg, nents, dir, attrs, true);
-}
-
-/**
- * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA
+ * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
  * @dev: valid struct device pointer
  * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
+ * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  *
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * The scatter gather list elements are merged together (if possible) and
- * tagged with the appropriate dma address and length. They are obtained via
- * sg_dma_{address,length}.
+ * Unmap a set of streaming mode DMA translations.  Again, CPU access
+ * rules concerning calls here are the same as for dma_unmap_single().
  */
-static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_map_sg(dev, sg, nents, dir, attrs, false);
-}
-
-static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir,
-		unsigned long attrs, bool is_coherent)
+static void arm_iommu_unmap_sg(struct device *dev,
+			       struct scatterlist *sg, int nents,
+			       enum dma_data_direction dir,
+			       unsigned long attrs)
 {
 	struct scatterlist *s;
 	int i;
@@ -1718,48 +1320,13 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
 		if (sg_dma_len(s))
 			__iommu_remove_mapping(dev, sg_dma_address(s),
 					       sg_dma_len(s));
-		if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 			__dma_page_dev_to_cpu(sg_page(s), s->offset,
 					      s->length, dir);
 	}
 }
 
 /**
- * arm_coherent_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer
- * @sg: list of buffers
- * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- *
- * Unmap a set of streaming mode DMA translations.  Again, CPU access
- * rules concerning calls here are the same as for dma_unmap_single().
- */
-static void arm_coherent_iommu_unmap_sg(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	__iommu_unmap_sg(dev, sg, nents, dir, attrs, true);
-}
-
-/**
- * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer
- * @sg: list of buffers
- * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- *
- * Unmap a set of streaming mode DMA translations.  Again, CPU access
- * rules concerning calls here are the same as for dma_unmap_single().
- */
-static void arm_iommu_unmap_sg(struct device *dev,
-			       struct scatterlist *sg, int nents,
-			       enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	__iommu_unmap_sg(dev, sg, nents, dir, attrs, false);
-}
-
-/**
  * arm_iommu_sync_sg_for_cpu
  * @dev: valid struct device pointer
  * @sg: list of buffers
@@ -1773,6 +1340,9 @@ static void arm_iommu_sync_sg_for_cpu(struct device *dev,
 	struct scatterlist *s;
 	int i;
 
+	if (dev->dma_coherent)
+		return;
+
 	for_each_sg(sg, s, nents, i)
 		__dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir);
 
@@ -1792,22 +1362,24 @@ static void arm_iommu_sync_sg_for_device(struct device *dev,
 	struct scatterlist *s;
 	int i;
 
+	if (dev->dma_coherent)
+		return;
+
 	for_each_sg(sg, s, nents, i)
 		__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 }
 
-
 /**
- * arm_coherent_iommu_map_page
+ * arm_iommu_map_page
  * @dev: valid struct device pointer
  * @page: page that buffer resides in
  * @offset: offset into page for start of buffer
  * @size: size of buffer to map
  * @dir: DMA transfer direction
  *
- * Coherent IOMMU aware version of arm_dma_map_page()
+ * IOMMU aware version of arm_dma_map_page()
  */
-static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *page,
+static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     unsigned long attrs)
 {
@@ -1815,6 +1387,9 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	dma_addr_t dma_addr;
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
+	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+
 	dma_addr = __alloc_iova(mapping, len);
 	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
@@ -1832,50 +1407,6 @@ fail:
 }
 
 /**
- * arm_iommu_map_page
- * @dev: valid struct device pointer
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * IOMMU aware version of arm_dma_map_page()
- */
-static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__dma_page_cpu_to_dev(page, offset, size, dir);
-
-	return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs);
-}
-
-/**
- * arm_coherent_iommu_unmap_page
- * @dev: valid struct device pointer
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_page)
- * @dir: DMA transfer direction (same as passed to dma_map_page)
- *
- * Coherent IOMMU aware version of arm_dma_unmap_page()
- */
-static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
-	dma_addr_t iova = handle & PAGE_MASK;
-	int offset = handle & ~PAGE_MASK;
-	int len = PAGE_ALIGN(size + offset);
-
-	if (!iova)
-		return;
-
-	iommu_unmap(mapping->domain, iova, len);
-	__free_iova(mapping, iova, len);
-}
-
-/**
  * arm_iommu_unmap_page
  * @dev: valid struct device pointer
  * @handle: DMA address of buffer
@@ -1889,15 +1420,17 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	struct page *page;
 	int offset = handle & ~PAGE_MASK;
 	int len = PAGE_ALIGN(size + offset);
 
 	if (!iova)
 		return;
 
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
+		page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 		__dma_page_dev_to_cpu(page, offset, size, dir);
+	}
 
 	iommu_unmap(mapping->domain, iova, len);
 	__free_iova(mapping, iova, len);
@@ -1965,12 +1498,13 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
 
-	if (!iova)
+	if (dev->dma_coherent || !iova)
 		return;
 
+	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	__dma_page_dev_to_cpu(page, offset, size, dir);
 }
 
@@ -1979,12 +1513,13 @@ static void arm_iommu_sync_single_for_device(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
 
-	if (!iova)
+	if (dev->dma_coherent || !iova)
 		return;
 
+	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
@@ -2006,26 +1541,6 @@ static const struct dma_map_ops iommu_ops = {
 
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
-
-	.dma_supported		= arm_dma_supported,
-};
-
-static const struct dma_map_ops iommu_coherent_ops = {
-	.alloc		= arm_coherent_iommu_alloc_attrs,
-	.free		= arm_coherent_iommu_free_attrs,
-	.mmap		= arm_coherent_iommu_mmap_attrs,
-	.get_sgtable	= arm_iommu_get_sgtable,
-
-	.map_page	= arm_coherent_iommu_map_page,
-	.unmap_page	= arm_coherent_iommu_unmap_page,
-
-	.map_sg		= arm_coherent_iommu_map_sg,
-	.unmap_sg	= arm_coherent_iommu_unmap_sg,
-
-	.map_resource	= arm_iommu_map_resource,
-	.unmap_resource	= arm_iommu_unmap_resource,
-
-	.dma_supported		= arm_dma_supported,
 };
 
 /**
@@ -2201,40 +1716,32 @@ void arm_iommu_detach_device(struct device *dev)
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
 	to_dma_iommu_mapping(dev) = NULL;
-	set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent));
+	set_dma_ops(dev, NULL);
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
-static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
-{
-	return coherent ? &iommu_coherent_ops : &iommu_ops;
-}
-
-static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu)
+static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				    const struct iommu_ops *iommu, bool coherent)
 {
 	struct dma_iommu_mapping *mapping;
 
-	if (!iommu)
-		return false;
-
 	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
 				size, dev_name(dev));
-		return false;
+		return;
 	}
 
 	if (__arm_iommu_attach_device(dev, mapping)) {
 		pr_warn("Failed to attached device %s to IOMMU_mapping\n",
 				dev_name(dev));
 		arm_iommu_release_mapping(mapping);
-		return false;
+		return;
 	}
 
-	return true;
+	set_dma_ops(dev, &iommu_ops);
 }
 
 static void arm_teardown_iommu_dma_ops(struct device *dev)
@@ -2250,27 +1757,20 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 
 #else
 
-static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu)
+static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				    const struct iommu_ops *iommu, bool coherent)
 {
-	return false;
 }
 
 static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 
-#define arm_get_iommu_dma_map_ops arm_get_dma_map_ops
-
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
 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;
-
 	dev->archdata.dma_coherent = coherent;
-#ifdef CONFIG_SWIOTLB
 	dev->dma_coherent = coherent;
-#endif
 
 	/*
 	 * Don't override the dma_ops if they have already been set. Ideally
@@ -2280,12 +1780,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu))
-		dma_ops = arm_get_iommu_dma_map_ops(coherent);
-	else
-		dma_ops = arm_get_dma_map_ops(coherent);
-
-	set_dma_ops(dev, dma_ops);
+	if (iommu)
+		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;
@@ -2301,7 +1797,6 @@ void arch_teardown_dma_ops(struct device *dev)
 	set_dma_ops(dev, NULL);
 }
 
-#ifdef CONFIG_SWIOTLB
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
@@ -2329,4 +1824,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 {
 	__arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false);
 }
-#endif /* CONFIG_SWIOTLB */