1 files changed, 50 insertions, 12 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3aac9..7f9b1798c6c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -250,7 +250,7 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 #ifdef CONFIG_MMU
 #ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#warning ARM Coherent DMA allocator does not (yet) support huge TLB
 #endif
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
@@ -880,10 +880,24 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
 
 	/*
-	 * Mark the D-cache clean for this page to avoid extra flushing.
+	 * Mark the D-cache clean for these pages to avoid extra flushing.
 	 */
-	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
-		set_bit(PG_dcache_clean, &page->flags);
+	if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+		unsigned long pfn;
+		size_t left = size;
+
+		pfn = page_to_pfn(page) + off / PAGE_SIZE;
+		off %= PAGE_SIZE;
+		if (off) {
+			pfn++;
+			left -= PAGE_SIZE - off;
+		}
+		while (left >= PAGE_SIZE) {
+			page = pfn_to_page(pfn++);
+			set_bit(PG_dcache_clean, &page->flags);
+			left -= PAGE_SIZE;
+		}
+	}
 }
 
 /**
@@ -1314,6 +1328,15 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (gfp & GFP_ATOMIC)
 		return __iommu_alloc_atomic(dev, size, handle);
 
+	/*
+	 * Following is a work-around (a.k.a. hack) to prevent pages
+	 * with __GFP_COMP being passed to split_page() which cannot
+	 * handle them.  The real problem is that this flag probably
+	 * should be 0 on ARM as it is not supported on this
+	 * platform; see CONFIG_HUGETLBFS.
+	 */
+	gfp &= ~(__GFP_COMP);
+
 	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
 	if (!pages)
 		return NULL;
@@ -1372,16 +1395,17 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			  dma_addr_t handle, struct dma_attrs *attrs)
 {
-	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
+	struct page **pages;
 	size = PAGE_ALIGN(size);
 
-	if (!pages) {
-		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+	if (__in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, cpu_addr, handle, size);
 		return;
 	}
 
-	if (__in_atomic_pool(cpu_addr, size)) {
-		__iommu_free_atomic(dev, cpu_addr, handle, size);
+	pages = __iommu_get_pages(cpu_addr, attrs);
+	if (!pages) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
 		return;
 	}
 
@@ -1636,13 +1660,27 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 	dma_addr_t dma_addr;
-	int ret, len = PAGE_ALIGN(size + offset);
+	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, 0);
+	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;
+	}
+
+	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)
 		goto fail;
 
@@ -1907,7 +1945,7 @@ void arm_iommu_detach_device(struct device *dev)
 
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
-	mapping = NULL;
+	dev->archdata.mapping = NULL;
 	set_dma_ops(dev, NULL);
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));