1 files changed, 75 insertions, 23 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f5e1a8471714..79f8b39801a8 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -159,7 +159,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static u64 get_coherent_dma_mask(struct device *dev)
 {
-	u64 mask = (u64)arm_dma_limit;
+	u64 mask = (u64)DMA_BIT_MASK(32);
 
 	if (dev) {
 		mask = dev->coherent_dma_mask;
@@ -173,10 +173,30 @@ static u64 get_coherent_dma_mask(struct device *dev)
 			return 0;
 		}
 
-		if ((~mask) & (u64)arm_dma_limit) {
-			dev_warn(dev, "coherent DMA mask %#llx is smaller "
-				 "than system GFP_DMA mask %#llx\n",
-				 mask, (u64)arm_dma_limit);
+		/*
+		 * If the mask allows for more memory than we can address,
+		 * and we actually have that much memory, then fail the
+		 * allocation.
+		 */
+		if (sizeof(mask) != sizeof(dma_addr_t) &&
+		    mask > (dma_addr_t)~0 &&
+		    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit) {
+			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
+				 mask);
+			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
+			return 0;
+		}
+
+		/*
+		 * Now check that the mask, when translated to a PFN,
+		 * fits within the allowable addresses which we can
+		 * allocate.
+		 */
+		if (dma_to_pfn(dev, mask) < arm_dma_pfn_limit) {
+			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
+				 mask,
+				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
+				 arm_dma_pfn_limit + 1);
 			return 0;
 		}
 	}
@@ -687,7 +707,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		    gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
@@ -700,7 +720,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
@@ -1007,8 +1027,27 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
  */
 int dma_supported(struct device *dev, u64 mask)
 {
-	if (mask < (u64)arm_dma_limit)
+	unsigned long limit;
+
+	/*
+	 * If the mask allows for more memory than we can address,
+	 * and we actually have that much memory, then we must
+	 * indicate that DMA to this device is not supported.
+	 */
+	if (sizeof(mask) != sizeof(dma_addr_t) &&
+	    mask > (dma_addr_t)~0 &&
+	    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit)
+		return 0;
+
+	/*
+	 * Translate the device's DMA mask to a PFN limit.  This
+	 * PFN number includes the page which we can DMA to.
+	 */
+	limit = dma_to_pfn(dev, mask);
+
+	if (limit < arm_dma_pfn_limit)
 		return 0;
+
 	return 1;
 }
 EXPORT_SYMBOL(dma_supported);
@@ -1232,7 +1271,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 				break;
 
 		len = (j - i) << PAGE_SHIFT;
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		ret = iommu_map(mapping->domain, iova, phys, len,
+				IOMMU_READ|IOMMU_WRITE);
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1431,6 +1471,27 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
+static int __dma_direction_to_prot(enum dma_data_direction dir)
+{
+	int prot;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		prot = IOMMU_READ | IOMMU_WRITE;
+		break;
+	case DMA_TO_DEVICE:
+		prot = IOMMU_READ;
+		break;
+	case DMA_FROM_DEVICE:
+		prot = IOMMU_WRITE;
+		break;
+	default:
+		prot = 0;
+	}
+
+	return prot;
+}
+
 /*
  * Map a part of the scatter-gather list into contiguous io address space
  */
@@ -1444,6 +1505,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int ret = 0;
 	unsigned int count;
 	struct scatterlist *s;
+	int prot;
 
 	size = PAGE_ALIGN(size);
 	*handle = DMA_ERROR_CODE;
@@ -1460,7 +1522,9 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		prot = __dma_direction_to_prot(dir);
+
+		ret = iommu_map(mapping->domain, iova, phys, len, prot);
 		if (ret < 0)
 			goto fail;
 		count += len >> PAGE_SHIFT;
@@ -1665,19 +1729,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
+	prot = __dma_direction_to_prot(dir);
 
 	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)