1 files changed, 97 insertions, 31 deletions

diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 7f8b37e85a2b..4dac4afc95a5 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -308,24 +308,15 @@ static void __swiotlb_sync_sg_for_device(struct device *dev,
 				       sg->length, dir);
 }
 
-static int __swiotlb_mmap(struct device *dev,
-			  struct vm_area_struct *vma,
-			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			  unsigned long attrs)
+static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
+			      unsigned long pfn, size_t size)
 {
 	int ret = -ENXIO;
 	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
 					PAGE_SHIFT;
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
-					     is_device_dma_coherent(dev));
-
-	if (dma_mmap_from_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,
@@ -336,19 +327,43 @@ static int __swiotlb_mmap(struct device *dev,
 	return ret;
 }
 
-static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
-				 void *cpu_addr, dma_addr_t handle, size_t size,
-				 unsigned long attrs)
+static int __swiotlb_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;
+	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+					     is_device_dma_coherent(dev));
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	return __swiotlb_mmap_pfn(vma, pfn, size);
+}
+
+static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
+				      struct page *page, size_t size)
 {
 	int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 
 	if (!ret)
-		sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)),
-			    PAGE_ALIGN(size), 0);
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
 
 	return ret;
 }
 
+static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+				 void *cpu_addr, dma_addr_t handle, size_t size,
+				 unsigned long attrs)
+{
+	struct page *page = phys_to_page(dma_to_phys(dev, handle));
+
+	return __swiotlb_get_sgtable_page(sgt, page, size);
+}
+
 static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
 	if (swiotlb)
@@ -584,20 +599,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 	 */
 	gfp |= __GFP_ZERO;
 
-	if (gfpflags_allow_blocking(gfp)) {
-		struct page **pages;
-		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
-
-		pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
-					handle, flush_page);
-		if (!pages)
-			return NULL;
-
-		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
-					      __builtin_return_address(0));
-		if (!addr)
-			iommu_dma_free(dev, pages, iosize, handle);
-	} else {
+	if (!gfpflags_allow_blocking(gfp)) {
 		struct page *page;
 		/*
 		 * In atomic context we can't remap anything, so we'll only
@@ -621,6 +623,45 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 				__free_from_pool(addr, size);
 			addr = NULL;
 		}
+	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+		struct page *page;
+
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+						 get_order(size), gfp);
+		if (!page)
+			return NULL;
+
+		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
+		if (iommu_dma_mapping_error(dev, *handle)) {
+			dma_release_from_contiguous(dev, page,
+						    size >> PAGE_SHIFT);
+			return NULL;
+		}
+		if (!coherent)
+			__dma_flush_area(page_to_virt(page), iosize);
+
+		addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+						   prot,
+						   __builtin_return_address(0));
+		if (!addr) {
+			iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
+			dma_release_from_contiguous(dev, page,
+						    size >> PAGE_SHIFT);
+		}
+	} else {
+		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+		struct page **pages;
+
+		pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
+					handle, flush_page);
+		if (!pages)
+			return NULL;
+
+		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
+					      __builtin_return_address(0));
+		if (!addr)
+			iommu_dma_free(dev, pages, iosize, handle);
 	}
 	return addr;
 }
@@ -632,7 +673,8 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 
 	size = PAGE_ALIGN(size);
 	/*
-	 * @cpu_addr will be one of 3 things depending on how it was allocated:
+	 * @cpu_addr will be one of 4 things depending on how it was allocated:
+	 * - A remapped array of pages for contiguous allocations.
 	 * - A remapped array of pages from iommu_dma_alloc(), for all
 	 *   non-atomic allocations.
 	 * - A non-cacheable alias from the atomic pool, for atomic
@@ -644,6 +686,12 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	if (__in_atomic_pool(cpu_addr, size)) {
 		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
 		__free_from_pool(cpu_addr, size);
+	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+		struct page *page = vmalloc_to_page(cpu_addr);
+
+		iommu_dma_unmap_page(dev, handle, iosize, 0, attrs);
+		dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
+		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
 	} else if (is_vmalloc_addr(cpu_addr)){
 		struct vm_struct *area = find_vm_area(cpu_addr);
 
@@ -670,6 +718,15 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
+	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+		/*
+		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+		 * hence in the vmalloc space.
+		 */
+		unsigned long pfn = vmalloc_to_pfn(cpu_addr);
+		return __swiotlb_mmap_pfn(vma, pfn, size);
+	}
+
 	area = find_vm_area(cpu_addr);
 	if (WARN_ON(!area || !area->pages))
 		return -ENXIO;
@@ -684,6 +741,15 @@ static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct vm_struct *area = find_vm_area(cpu_addr);
 
+	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+		/*
+		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+		 * hence in the vmalloc space.
+		 */
+		struct page *page = vmalloc_to_page(cpu_addr);
+		return __swiotlb_get_sgtable_page(sgt, page, size);
+	}
+
 	if (WARN_ON(!area || !area->pages))
 		return -ENXIO;