swiotlb: support aligned swiotlb buffers

Add an argument to swiotlb_tbl_map_single that specifies the desired
alignment of the allocated buffer. This is used by dma-iommu to ensure
the buffer is aligned to the iova granule size when using swiotlb with
untrusted sub-granule mappings. This addresses an issue where adjacent
slots could be exposed to the untrusted device if IO_TLB_SIZE < iova
granule < PAGE_SIZE.

Signed-off-by: David Stevens <stevensd@chromium.org>

drivers/iommu/dma-iommu.c

@@ -802,8 +802,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 		size_t padding_size;
 
 		aligned_size = iova_align(iovad, size);
-		phys = swiotlb_tbl_map_single(dev, phys, size,
-					      aligned_size, dir, attrs);
+		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
+					      iova_mask(iovad), dir, attrs);
 
 		if (phys == DMA_MAPPING_ERROR)
 			return DMA_MAPPING_ERROR;

include/linux/swiotlb.h

@@ -44,7 +44,8 @@ extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
 		size_t mapping_size, size_t alloc_size,
-		enum dma_data_direction dir, unsigned long attrs);
+		unsigned int alloc_aligned_mask, enum dma_data_direction dir,
+		unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,

kernel/dma/swiotlb.c

@@ -427,7 +427,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
  * allocate a buffer from that IO TLB pool.
  */
 static int find_slots(struct device *dev, phys_addr_t orig_addr,
-		size_t alloc_size)
+		size_t alloc_size, unsigned int alloc_align_mask)
 {
 	struct io_tlb_mem *mem = io_tlb_default_mem;
 	unsigned long boundary_mask = dma_get_seg_boundary(dev);
@@ -450,6 +450,7 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,
 	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
 	if (alloc_size >= PAGE_SIZE)
 		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
+	stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1);
 
 	spin_lock_irqsave(&mem->lock, flags);
 	if (unlikely(nslots > mem->nslabs - mem->used))
@@ -504,7 +505,8 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,
 
 phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		size_t mapping_size, size_t alloc_size,
-		enum dma_data_direction dir, unsigned long attrs)
+		unsigned int alloc_align_mask, enum dma_data_direction dir,
+		unsigned long attrs)
 {
 	struct io_tlb_mem *mem = io_tlb_default_mem;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
@@ -524,7 +526,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
-	index = find_slots(dev, orig_addr, alloc_size + offset);
+	index = find_slots(dev, orig_addr,
+			   alloc_size + offset, alloc_align_mask);
 	if (index == -1) {
 		if (!(attrs & DMA_ATTR_NO_WARN))
 			dev_warn_ratelimited(dev,
@@ -636,7 +639,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
 			      swiotlb_force);
 
-	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
 			attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;