drm: msm: fix common struct sg_table related issues

The Documentation/DMA-API-HOWTO.txt states that the dma_map_sg() function
returns the number of the created entries in the DMA address space.
However the subsequent calls to the dma_sync_sg_for_{device,cpu}() and
dma_unmap_sg must be called with the original number of the entries
passed to the dma_map_sg().

struct sg_table is a common structure used for describing a non-contiguous
memory buffer, used commonly in the DRM and graphics subsystems. It
consists of a scatterlist with memory pages and DMA addresses (sgl entry),
as well as the number of scatterlist entries: CPU pages (orig_nents entry)
and DMA mapped pages (nents entry).

It turned out that it was a common mistake to misuse nents and orig_nents
entries, calling DMA-mapping functions with a wrong number of entries or
ignoring the number of mapped entries returned by the dma_map_sg()
function.

To avoid such issues, lets use a common dma-mapping wrappers operating
directly on the struct sg_table objects and use scatterlist page
iterators where possible. This, almost always, hides references to the
nents and orig_nents entries, making the code robust, easier to follow
and copy/paste safe.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Rob Clark <robdclark@gmail.com>

drivers/gpu/drm/msm/msm_gem.c

@@ -53,11 +53,10 @@ static void sync_for_device(struct msm_gem_object *msm_obj)
 	struct device *dev = msm_obj->base.dev->dev;
 
 	if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) {
-		dma_sync_sg_for_device(dev, msm_obj->sgt->sgl,
-			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+		dma_sync_sgtable_for_device(dev, msm_obj->sgt,
+					    DMA_BIDIRECTIONAL);
 	} else {
-		dma_map_sg(dev, msm_obj->sgt->sgl,
-			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+		dma_map_sgtable(dev, msm_obj->sgt, DMA_BIDIRECTIONAL, 0);
 	}
 }
 
@@ -66,11 +65,9 @@ static void sync_for_cpu(struct msm_gem_object *msm_obj)
 	struct device *dev = msm_obj->base.dev->dev;
 
 	if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) {
-		dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl,
-			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+		dma_sync_sgtable_for_cpu(dev, msm_obj->sgt, DMA_BIDIRECTIONAL);
 	} else {
-		dma_unmap_sg(dev, msm_obj->sgt->sgl,
-			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+		dma_unmap_sgtable(dev, msm_obj->sgt, DMA_BIDIRECTIONAL, 0);
 	}
 }
 

drivers/gpu/drm/msm/msm_gpummu.c

@@ -30,21 +30,20 @@ static int msm_gpummu_map(struct msm_mmu *mmu, uint64_t iova,
 {
 	struct msm_gpummu *gpummu = to_msm_gpummu(mmu);
 	unsigned idx = (iova - GPUMMU_VA_START) / GPUMMU_PAGE_SIZE;
-	struct scatterlist *sg;
+	struct sg_dma_page_iter dma_iter;
 	unsigned prot_bits = 0;
-	unsigned i, j;
 
 	if (prot & IOMMU_WRITE)
 		prot_bits |= 1;
 	if (prot & IOMMU_READ)
 		prot_bits |= 2;
 
-	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
-		dma_addr_t addr = sg->dma_address;
-		for (j = 0; j < sg->length / GPUMMU_PAGE_SIZE; j++, idx++) {
-			gpummu->table[idx] = addr | prot_bits;
-			addr += GPUMMU_PAGE_SIZE;
-		}
+	for_each_sgtable_dma_page(sgt, &dma_iter, 0) {
+		dma_addr_t addr = sg_page_iter_dma_address(&dma_iter);
+		int i;
+
+		for (i = 0; i < PAGE_SIZE; i += GPUMMU_PAGE_SIZE)
+			gpummu->table[idx++] = (addr + i) | prot_bits;
 	}
 
 	/* we can improve by deferring flush for multiple map() */

drivers/gpu/drm/msm/msm_iommu.c

@@ -36,7 +36,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 	size_t ret;
 
-	ret = iommu_map_sg(iommu->domain, iova, sgt->sgl, sgt->nents, prot);
+	ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot);
 	WARN_ON(!ret);
 
 	return (ret == len) ? 0 : -EINVAL;