On Thu, 2015-10-01 at 20:13 +0100, Robin Murphy wrote:
[...]

+/*
+ * The DMA API client is passing in a scatterlist which could describe
+ * any old buffer layout, but the IOMMU API requires everything to be
+ * aligned to IOMMU pages. Hence the need for this complicated bit of
+ * impedance-matching, to be able to hand off a suitably-aligned list,
+ * but still preserve the original offsets and sizes for the caller.
+ */
+int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, int prot)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iova_domain *iovad = domain->iova_cookie;
+	struct iova *iova;
+	struct scatterlist *s, *prev = NULL;
+	dma_addr_t dma_addr;
+	size_t iova_len = 0;
+	int i;
+
+	/*
+	 * Work out how much IOVA space we need, and align the segments to
+	 * IOVA granules for the IOMMU driver to handle. With some clever
+	 * trickery we can modify the list in-place, but reversibly, by
+	 * hiding the original data in the as-yet-unused DMA fields.
+	 */
+	for_each_sg(sg, s, nents, i) {
+		size_t s_offset = iova_offset(iovad, s->offset);
+		size_t s_length = s->length;
+
+		sg_dma_address(s) = s->offset;
+		sg_dma_len(s) = s_length;
+		s->offset -= s_offset;
+		s_length = iova_align(iovad, s_length + s_offset);
+		s->length = s_length;
+
+		/*
+		 * The simple way to avoid the rare case of a segment
+		 * crossing the boundary mask is to pad the previous one
+		 * to end at a naturally-aligned IOVA for this one's size,
+		 * at the cost of potentially over-allocating a little.
+		 */
+		if (prev) {
+			size_t pad_len = roundup_pow_of_two(s_length);
+
+			pad_len = (pad_len - iova_len) & (pad_len - 1);
+			prev->length += pad_len;

Hi Robin,
      While our v4l2 testing, It seems that we met a problem here.
      Here we update prev->length again, Do we need update
sg_dma_len(prev) again too?

      Some function like vb2_dc_get_contiguous_size[1] always get
sg_dma_len(s) to compare instead of s->length. so it may break
unexpectedly while sg_dma_len(s) is not same with s->length.

[1]:
http://lxr.free-electrons.com/source/drivers/media/v4l2-core/videobuf2-dma-contig.c#L70

+			iova_len += pad_len;
+		}
+
+		iova_len += s_length;
+		prev = s;
+	}
+
+	iova = __alloc_iova(iovad, iova_len, dma_get_mask(dev));
+	if (!iova)
+		goto out_restore_sg;
+
+	/*
+	 * We'll leave any physical concatenation to the IOMMU driver's
+	 * implementation - it knows better than we do.
+	 */
+	dma_addr = iova_dma_addr(iovad, iova);
+	if (iommu_map_sg(domain, dma_addr, sg, nents, prot) < iova_len)
+		goto out_free_iova;
+
+	return __finalise_sg(dev, sg, nents, dma_addr);
+
+out_free_iova:
+	__free_iova(iovad, iova);
+out_restore_sg:
+	__invalidate_sg(sg, nents);
+	return 0;
+}
+