Merge branch 'for-5.10-drm-sg-fix' of https://github.com/mszyprow/linux into drm-next

Please pull a set of fixes for various DRM drivers that finally resolve
incorrect usage of the scatterlists (struct sg_table nents and orig_nents
entries), what causes issues when IOMMU is used.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200910080505.24456-1-m.szyprowski@samsung.com

drivers/dma-buf/heaps/heap-helpers.c

@@ -140,13 +140,12 @@ struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment,
 				      enum dma_data_direction direction)
 {
 	struct dma_heaps_attachment *a = attachment->priv;
-	struct sg_table *table;
-
-	table = &a->table;
+	struct sg_table *table = &a->table;
+	int ret;
 
-	if (!dma_map_sg(attachment->dev, table->sgl, table->nents,
-			direction))
-		table = ERR_PTR(-ENOMEM);
+	ret = dma_map_sgtable(attachment->dev, table, direction, 0);
+	if (ret)
+		table = ERR_PTR(ret);
 	return table;
 }
 
@@ -154,7 +153,7 @@ static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,
 				   struct sg_table *table,
 				   enum dma_data_direction direction)
 {
-	dma_unmap_sg(attachment->dev, table->sgl, table->nents, direction);
+	dma_unmap_sgtable(attachment->dev, table, direction, 0);
 }
 
 static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf)

drivers/dma-buf/udmabuf.c

@@ -63,10 +63,9 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
 					GFP_KERNEL);
 	if (ret < 0)
 		goto err;
-	if (!dma_map_sg(dev, sg->sgl, sg->nents, direction)) {
-		ret = -EINVAL;
+	ret = dma_map_sgtable(dev, sg, direction, 0);
+	if (ret < 0)
 		goto err;
-	}
 	return sg;
 
 err:
@@ -78,7 +77,7 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
 static void put_sg_table(struct device *dev, struct sg_table *sg,
 			 enum dma_data_direction direction)
 {
-	dma_unmap_sg(dev, sg->sgl, sg->nents, direction);
+	dma_unmap_sgtable(dev, sg, direction, 0);
 	sg_free_table(sg);
 	kfree(sg);
 }

drivers/gpu/drm/armada/armada_gem.c

@@ -379,7 +379,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 	struct armada_gem_object *dobj = drm_to_armada_gem(obj);
 	struct scatterlist *sg;
 	struct sg_table *sgt;
-	int i, num;
+	int i;
 
 	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
 	if (!sgt)
@@ -395,22 +395,18 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 
 		mapping = dobj->obj.filp->f_mapping;
 
-		for_each_sg(sgt->sgl, sg, count, i) {
+		for_each_sgtable_sg(sgt, sg, i) {
 			struct page *page;
 
 			page = shmem_read_mapping_page(mapping, i);
-			if (IS_ERR(page)) {
-				num = i;
+			if (IS_ERR(page))
 				goto release;
-			}
 
 			sg_set_page(sg, page, PAGE_SIZE, 0);
 		}
 
-		if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) {
-			num = sgt->nents;
+		if (dma_map_sgtable(attach->dev, sgt, dir, 0))
 			goto release;
-		}
 	} else if (dobj->page) {
 		/* Single contiguous page */
 		if (sg_alloc_table(sgt, 1, GFP_KERNEL))
@@ -418,7 +414,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 
 		sg_set_page(sgt->sgl, dobj->page, dobj->obj.size, 0);
 
-		if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0)
+		if (dma_map_sgtable(attach->dev, sgt, dir, 0))
 			goto free_table;
 	} else if (dobj->linear) {
 		/* Single contiguous physical region - no struct page */
@@ -432,7 +428,8 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 	return sgt;
 
  release:
-	for_each_sg(sgt->sgl, sg, num, i)
+	for_each_sgtable_sg(sgt, sg, i)
+		if (sg_page(sg))
 			put_page(sg_page(sg));
  free_table:
 	sg_free_table(sgt);
@@ -449,11 +446,12 @@ static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
 	int i;
 
 	if (!dobj->linear)
-		dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 
 	if (dobj->obj.filp) {
 		struct scatterlist *sg;
-		for_each_sg(sgt->sgl, sg, sgt->nents, i)
+
+		for_each_sgtable_sg(sgt, sg, i)
 			put_page(sg_page(sg));
 	}
 

drivers/gpu/drm/drm_cache.c

@@ -127,7 +127,7 @@ drm_clflush_sg(struct sg_table *st)
 		struct sg_page_iter sg_iter;
 
 		mb(); /*CLFLUSH is ordered only by using memory barriers*/
-		for_each_sg_page(st->sgl, &sg_iter, st->nents, 0)
+		for_each_sgtable_page(st, &sg_iter, 0)
 			drm_clflush_page(sg_page_iter_page(&sg_iter));
 		mb(); /*Make sure that all cache line entry is flushed*/
 

drivers/gpu/drm/drm_gem_cma_helper.c

@@ -471,27 +471,10 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev,
 {
 	struct drm_gem_cma_object *cma_obj;
 
-	if (sgt->nents != 1) {
 	/* check if the entries in the sg_table are contiguous */
-		dma_addr_t next_addr = sg_dma_address(sgt->sgl);
-		struct scatterlist *s;
-		unsigned int i;
-
-		for_each_sg(sgt->sgl, s, sgt->nents, i) {
-			/*
-			 * sg_dma_address(s) is only valid for entries
-			 * that have sg_dma_len(s) != 0
-			 */
-			if (!sg_dma_len(s))
-				continue;
-
-			if (sg_dma_address(s) != next_addr)
+	if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size)
 		return ERR_PTR(-EINVAL);
 
-			next_addr = sg_dma_address(s) + sg_dma_len(s);
-		}
-	}
-
 	/* Create a CMA GEM buffer. */
 	cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size);
 	if (IS_ERR(cma_obj))

drivers/gpu/drm/drm_gem_shmem_helper.c

@@ -126,8 +126,8 @@ void drm_gem_shmem_free_object(struct drm_gem_object *obj)
 		drm_prime_gem_destroy(obj, shmem->sgt);
 	} else {
 		if (shmem->sgt) {
-			dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl,
-				     shmem->sgt->nents, DMA_BIDIRECTIONAL);
+			dma_unmap_sgtable(obj->dev->dev, shmem->sgt,
+					  DMA_BIDIRECTIONAL, 0);
 			sg_free_table(shmem->sgt);
 			kfree(shmem->sgt);
 		}
@@ -424,8 +424,7 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
 
 	WARN_ON(!drm_gem_shmem_is_purgeable(shmem));
 
-	dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl,
-		     shmem->sgt->nents, DMA_BIDIRECTIONAL);
+	dma_unmap_sgtable(obj->dev->dev, shmem->sgt, DMA_BIDIRECTIONAL, 0);
 	sg_free_table(shmem->sgt);
 	kfree(shmem->sgt);
 	shmem->sgt = NULL;
@@ -697,12 +696,17 @@ struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_object *obj)
 		goto err_put_pages;
 	}
 	/* Map the pages for use by the h/w. */
-	dma_map_sg(obj->dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL);
+	ret = dma_map_sgtable(obj->dev->dev, sgt, DMA_BIDIRECTIONAL, 0);
+	if (ret)
+		goto err_free_sgt;
 
 	shmem->sgt = sgt;
 
 	return sgt;
 
+err_free_sgt:
+	sg_free_table(sgt);
+	kfree(sgt);
 err_put_pages:
 	drm_gem_shmem_put_pages(shmem);
 	return ERR_PTR(ret);

drivers/gpu/drm/drm_prime.c

@@ -617,6 +617,7 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 {
 	struct drm_gem_object *obj = attach->dmabuf->priv;
 	struct sg_table *sgt;
+	int ret;
 
 	if (WARN_ON(dir == DMA_NONE))
 		return ERR_PTR(-EINVAL);
@@ -626,11 +627,12 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 	else
 		sgt = obj->dev->driver->gem_prime_get_sg_table(obj);
 
-	if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
-			      DMA_ATTR_SKIP_CPU_SYNC)) {
+	ret = dma_map_sgtable(attach->dev, sgt, dir,
+			      DMA_ATTR_SKIP_CPU_SYNC);
+	if (ret) {
 		sg_free_table(sgt);
 		kfree(sgt);
-		sgt = ERR_PTR(-ENOMEM);
+		sgt = ERR_PTR(ret);
 	}
 
 	return sgt;
@@ -652,8 +654,7 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 	if (!sgt)
 		return;
 
-	dma_unmap_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
-			   DMA_ATTR_SKIP_CPU_SYNC);
+	dma_unmap_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC);
 	sg_free_table(sgt);
 	kfree(sgt);
 }
@@ -825,6 +826,37 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page
 }
 EXPORT_SYMBOL(drm_prime_pages_to_sg);
 
+/**
+ * drm_prime_get_contiguous_size - returns the contiguous size of the buffer
+ * @sgt: sg_table describing the buffer to check
+ *
+ * This helper calculates the contiguous size in the DMA address space
+ * of the the buffer described by the provided sg_table.
+ *
+ * This is useful for implementing
+ * &drm_gem_object_funcs.gem_prime_import_sg_table.
+ */
+unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt)
+{
+	dma_addr_t expected = sg_dma_address(sgt->sgl);
+	struct scatterlist *sg;
+	unsigned long size = 0;
+	int i;
+
+	for_each_sgtable_dma_sg(sgt, sg, i) {
+		unsigned int len = sg_dma_len(sg);
+
+		if (!len)
+			break;
+		if (sg_dma_address(sg) != expected)
+			break;
+		expected += len;
+		size += len;
+	}
+	return size;
+}
+EXPORT_SYMBOL(drm_prime_get_contiguous_size);
+
 /**
  * drm_gem_prime_export - helper library implementation of the export callback
  * @obj: GEM object to export
@@ -959,45 +991,26 @@ EXPORT_SYMBOL(drm_gem_prime_import);
 int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages,
 				     dma_addr_t *addrs, int max_entries)
 {
-	unsigned count;
-	struct scatterlist *sg;
-	struct page *page;
-	u32 page_len, page_index;
-	dma_addr_t addr;
-	u32 dma_len, dma_index;
-
-	/*
-	 * Scatterlist elements contains both pages and DMA addresses, but
-	 * one shoud not assume 1:1 relation between them. The sg->length is
-	 * the size of the physical memory chunk described by the sg->page,
-	 * while sg_dma_len(sg) is the size of the DMA (IO virtual) chunk
-	 * described by the sg_dma_address(sg).
-	 */
-	page_index = 0;
-	dma_index = 0;
-	for_each_sg(sgt->sgl, sg, sgt->nents, count) {
-		page_len = sg->length;
-		page = sg_page(sg);
-		dma_len = sg_dma_len(sg);
-		addr = sg_dma_address(sg);
-
-		while (pages && page_len > 0) {
-			if (WARN_ON(page_index >= max_entries))
+	struct sg_dma_page_iter dma_iter;
+	struct sg_page_iter page_iter;
+	struct page **p = pages;
+	dma_addr_t *a = addrs;
+
+	if (pages) {
+		for_each_sgtable_page(sgt, &page_iter, 0) {
+			if (WARN_ON(p - pages >= max_entries))
 				return -1;
-			pages[page_index] = page;
-			page++;
-			page_len -= PAGE_SIZE;
-			page_index++;
+			*p++ = sg_page_iter_page(&page_iter);
 		}
-		while (addrs && dma_len > 0) {
-			if (WARN_ON(dma_index >= max_entries))
+	}
+	if (addrs) {
+		for_each_sgtable_dma_page(sgt, &dma_iter, 0) {
+			if (WARN_ON(a - addrs >= max_entries))
 				return -1;
-			addrs[dma_index] = addr;
-			addr += PAGE_SIZE;
-			dma_len -= PAGE_SIZE;
-			dma_index++;
+			*a++ = sg_page_iter_dma_address(&dma_iter);
 		}
 	}
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_prime_sg_to_page_addr_arrays);

drivers/gpu/drm/etnaviv/etnaviv_gem.c

@@ -27,7 +27,7 @@ static void etnaviv_gem_scatter_map(struct etnaviv_gem_object *etnaviv_obj)
 	 * because display controller, GPU, etc. are not coherent.
 	 */
 	if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK)
-		dma_map_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL);
+		dma_map_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0);
 }
 
 static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj)
@@ -51,7 +51,7 @@ static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj
 	 * discard those writes.
 	 */
 	if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK)
-		dma_unmap_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL);
+		dma_unmap_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0);
 }
 
 /* called with etnaviv_obj->lock held */
@@ -404,8 +404,7 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op,
 	}
 
 	if (etnaviv_obj->flags & ETNA_BO_CACHED) {
-		dma_sync_sg_for_cpu(dev->dev, etnaviv_obj->sgt->sgl,
-				    etnaviv_obj->sgt->nents,
+		dma_sync_sgtable_for_cpu(dev->dev, etnaviv_obj->sgt,
 					 etnaviv_op_to_dma_dir(op));
 		etnaviv_obj->last_cpu_prep_op = op;
 	}
@@ -421,8 +420,7 @@ int etnaviv_gem_cpu_fini(struct drm_gem_object *obj)
 	if (etnaviv_obj->flags & ETNA_BO_CACHED) {
 		/* fini without a prep is almost certainly a userspace error */
 		WARN_ON(etnaviv_obj->last_cpu_prep_op == 0);
-		dma_sync_sg_for_device(dev->dev, etnaviv_obj->sgt->sgl,
-			etnaviv_obj->sgt->nents,
+		dma_sync_sgtable_for_device(dev->dev, etnaviv_obj->sgt,
 			etnaviv_op_to_dma_dir(etnaviv_obj->last_cpu_prep_op));
 		etnaviv_obj->last_cpu_prep_op = 0;
 	}

drivers/gpu/drm/etnaviv/etnaviv_mmu.c

@@ -73,13 +73,13 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova,
 			     struct sg_table *sgt, unsigned len, int prot)
 {	struct scatterlist *sg;
 	unsigned int da = iova;
-	unsigned int i, j;
+	unsigned int i;
 	int ret;
 
 	if (!context || !sgt)
 		return -EINVAL;
 
-	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+	for_each_sgtable_dma_sg(sgt, sg, i) {
 		u32 pa = sg_dma_address(sg) - sg->offset;
 		size_t bytes = sg_dma_len(sg) + sg->offset;
 
@@ -95,14 +95,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova,
 	return 0;
 
 fail:
-	da = iova;
-
-	for_each_sg(sgt->sgl, sg, i, j) {
-		size_t bytes = sg_dma_len(sg) + sg->offset;
-
-		etnaviv_context_unmap(context, da, bytes);
-		da += bytes;
-	}
+	etnaviv_context_unmap(context, iova, da - iova);
 	return ret;
 }
 
@@ -113,7 +106,7 @@ static void etnaviv_iommu_unmap(struct etnaviv_iommu_context *context, u32 iova,
 	unsigned int da = iova;
 	int i;
 
-	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+	for_each_sgtable_dma_sg(sgt, sg, i) {
 		size_t bytes = sg_dma_len(sg) + sg->offset;
 
 		etnaviv_context_unmap(context, da, bytes);

drivers/gpu/drm/exynos/exynos_drm_g2d.c

@@ -395,8 +395,8 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
 		return;
 
 out:
-	dma_unmap_sg(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt->sgl,
-			g2d_userptr->sgt->nents, DMA_BIDIRECTIONAL);
+	dma_unmap_sgtable(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt,
+			  DMA_BIDIRECTIONAL, 0);
 
 	pages = frame_vector_pages(g2d_userptr->vec);
 	if (!IS_ERR(pages)) {
@@ -511,10 +511,10 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 
 	g2d_userptr->sgt = sgt;
 
-	if (!dma_map_sg(to_dma_dev(g2d->drm_dev), sgt->sgl, sgt->nents,
-				DMA_BIDIRECTIONAL)) {
+	ret = dma_map_sgtable(to_dma_dev(g2d->drm_dev), sgt,
+			      DMA_BIDIRECTIONAL, 0);
+	if (ret) {
 		DRM_DEV_ERROR(g2d->dev, "failed to map sgt with dma region.\n");
-		ret = -ENOMEM;
 		goto err_sg_free_table;
 	}
 

drivers/gpu/drm/exynos/exynos_drm_gem.c

@@ -431,28 +431,11 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev,
 {
 	struct exynos_drm_gem *exynos_gem;
 
-	if (sgt->nents < 1)
-		return ERR_PTR(-EINVAL);
-
-	/*
-	 * Check if the provided buffer has been mapped as contiguous
-	 * into DMA address space.
-	 */
-	if (sgt->nents > 1) {
-		dma_addr_t next_addr = sg_dma_address(sgt->sgl);
-		struct scatterlist *s;
-		unsigned int i;
-
-		for_each_sg(sgt->sgl, s, sgt->nents, i) {
-			if (!sg_dma_len(s))
-				break;
-			if (sg_dma_address(s) != next_addr) {
+	/* check if the entries in the sg_table are contiguous */
+	if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size) {
 		DRM_ERROR("buffer chunks must be mapped contiguously");
 		return ERR_PTR(-EINVAL);
 	}
-			next_addr = sg_dma_address(s) + sg_dma_len(s);
-		}
-	}
 
 	exynos_gem = exynos_drm_gem_init(dev, attach->dmabuf->size);
 	if (IS_ERR(exynos_gem))

drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c

@@ -48,12 +48,9 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme
 		src = sg_next(src);
 	}
 
-	if (!dma_map_sg_attrs(attachment->dev,
-			      st->sgl, st->nents, dir,
-			      DMA_ATTR_SKIP_CPU_SYNC)) {
-		ret = -ENOMEM;
+	ret = dma_map_sgtable(attachment->dev, st, dir, DMA_ATTR_SKIP_CPU_SYNC);
+	if (ret)
 		goto err_free_sg;
-	}
 
 	return st;
 
@@ -73,9 +70,7 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
 
-	dma_unmap_sg_attrs(attachment->dev,
-			   sg->sgl, sg->nents, dir,
-			   DMA_ATTR_SKIP_CPU_SYNC);
+	dma_unmap_sgtable(attachment->dev, sg, dir, DMA_ATTR_SKIP_CPU_SYNC);
 	sg_free_table(sg);
 	kfree(sg);
 

drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c

@@ -28,10 +28,9 @@ static struct sg_table *mock_map_dma_buf(struct dma_buf_attachment *attachment,
 		sg = sg_next(sg);
 	}
 
-	if (!dma_map_sg(attachment->dev, st->sgl, st->nents, dir)) {
-		err = -ENOMEM;
+	err = dma_map_sgtable(attachment->dev, st, dir, 0);
+	if (err)
 		goto err_st;
-	}
 
 	return st;
 
@@ -46,7 +45,7 @@ static void mock_unmap_dma_buf(struct dma_buf_attachment *attachment,
 			       struct sg_table *st,
 			       enum dma_data_direction dir)
 {
-	dma_unmap_sg(attachment->dev, st->sgl, st->nents, dir);
+	dma_unmap_sgtable(attachment->dev, st, dir, 0);
 	sg_free_table(st);
 	kfree(st);
 }

drivers/gpu/drm/lima/lima_gem.c

@@ -69,8 +69,7 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
 		return ret;
 
 	if (bo->base.sgt) {
-		dma_unmap_sg(dev, bo->base.sgt->sgl,
-			     bo->base.sgt->nents, DMA_BIDIRECTIONAL);
+		dma_unmap_sgtable(dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
 		sg_free_table(bo->base.sgt);
 	} else {
 		bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL);
@@ -80,7 +79,13 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
 		}
 	}
 
-	dma_map_sg(dev, sgt.sgl, sgt.nents, DMA_BIDIRECTIONAL);
+	ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0);
+	if (ret) {
+		sg_free_table(&sgt);
+		kfree(bo->base.sgt);
+		bo->base.sgt = NULL;
+		return ret;
+	}
 
 	*bo->base.sgt = sgt;
 

drivers/gpu/drm/lima/lima_vm.c

@@ -124,7 +124,7 @@ int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create)
 	if (err)
 		goto err_out1;
 
-	for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter, bo->base.sgt->nents, 0) {
+	for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, 0) {
 		err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
 				       bo_va->node.start + offset);
 		if (err)
@@ -298,8 +298,7 @@ int lima_vm_map_bo(struct lima_vm *vm, struct lima_bo *bo, int pageoff)
 	mutex_lock(&vm->lock);
 
 	base = bo_va->node.start + (pageoff << PAGE_SHIFT);
-	for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter,
-			     bo->base.sgt->nents, pageoff) {
+	for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, pageoff) {
 		err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
 				       base + offset);
 		if (err)

drivers/gpu/drm/mediatek/mtk_drm_gem.c

@@ -212,46 +212,28 @@ struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
 			struct dma_buf_attachment *attach, struct sg_table *sg)
 {
 	struct mtk_drm_gem_obj *mtk_gem;
-	int ret;
-	struct scatterlist *s;
-	unsigned int i;
-	dma_addr_t expected;
 
-	mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size);
+	/* check if the entries in the sg_table are contiguous */
+	if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) {
+		DRM_ERROR("sg_table is not contiguous");
+		return ERR_PTR(-EINVAL);
+	}
 
+	mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size);
 	if (IS_ERR(mtk_gem))
 		return ERR_CAST(mtk_gem);
 
-	expected = sg_dma_address(sg->sgl);
-	for_each_sg(sg->sgl, s, sg->nents, i) {
-		if (!sg_dma_len(s))
-			break;
-
-		if (sg_dma_address(s) != expected) {
-			DRM_ERROR("sg_table is not contiguous");
-			ret = -EINVAL;
-			goto err_gem_free;
-		}
-		expected = sg_dma_address(s) + sg_dma_len(s);
-	}
-
 	mtk_gem->dma_addr = sg_dma_address(sg->sgl);
 	mtk_gem->sg = sg;
 
 	return &mtk_gem->base;
-
-err_gem_free:
-	kfree(mtk_gem);
-	return ERR_PTR(ret);
 }
 
 void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
 	struct sg_table *sgt;
-	struct sg_page_iter iter;
 	unsigned int npages;
-	unsigned int i = 0;
 
 	if (mtk_gem->kvaddr)
 		return mtk_gem->kvaddr;
@@ -265,11 +247,8 @@ void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)
 	if (!mtk_gem->pages)
 		goto out;
 
-	for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) {
-		mtk_gem->pages[i++] = sg_page_iter_page(&iter);
-		if (i > npages)
-			break;
-	}
+	drm_prime_sg_to_page_addr_arrays(sgt, mtk_gem->pages, NULL, npages);
+
 	mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP,
 			       pgprot_writecombine(PAGE_KERNEL));
 

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;

drivers/gpu/drm/omapdrm/omap_gem.c

@@ -1297,10 +1297,9 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size,
 		omap_obj->dma_addr = sg_dma_address(sgt->sgl);
 	} else {
 		/* Create pages list from sgt */
-		struct sg_page_iter iter;
 		struct page **pages;
 		unsigned int npages;
-		unsigned int i = 0;
+		unsigned int ret;
 
 		npages = DIV_ROUND_UP(size, PAGE_SIZE);
 		pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL);
@@ -1311,14 +1310,9 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size,
 		}
 
 		omap_obj->pages = pages;
-
-		for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) {
-			pages[i++] = sg_page_iter_page(&iter);
-			if (i > npages)
-				break;
-		}
-
-		if (WARN_ON(i != npages)) {
+		ret = drm_prime_sg_to_page_addr_arrays(sgt, pages, NULL,
+						       npages);
+		if (ret) {
 			omap_gem_free_object(obj);
 			obj = ERR_PTR(-ENOMEM);
 			goto done;

drivers/gpu/drm/panfrost/panfrost_gem.c

@@ -41,8 +41,8 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj)
 
 		for (i = 0; i < n_sgt; i++) {
 			if (bo->sgts[i].sgl) {
-				dma_unmap_sg(pfdev->dev, bo->sgts[i].sgl,
-					     bo->sgts[i].nents, DMA_BIDIRECTIONAL);
+				dma_unmap_sgtable(pfdev->dev, &bo->sgts[i],
+						  DMA_BIDIRECTIONAL, 0);
 				sg_free_table(&bo->sgts[i]);
 			}
 		}

drivers/gpu/drm/panfrost/panfrost_mmu.c

@@ -253,7 +253,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 	struct io_pgtable_ops *ops = mmu->pgtbl_ops;
 	u64 start_iova = iova;
 
-	for_each_sg(sgt->sgl, sgl, sgt->nents, count) {
+	for_each_sgtable_dma_sg(sgt, sgl, count) {
 		unsigned long paddr = sg_dma_address(sgl);
 		size_t len = sg_dma_len(sgl);
 
@@ -517,10 +517,9 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
 	if (ret)
 		goto err_pages;
 
-	if (!dma_map_sg(pfdev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL)) {
-		ret = -EINVAL;
+	ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0);
+	if (ret)
 		goto err_map;
-	}
 
 	mmu_map_sg(pfdev, bomapping->mmu, addr,
 		   IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);

drivers/gpu/drm/rcar-du/rcar_du_vsp.c

@@ -197,9 +197,8 @@ int rcar_du_vsp_map_fb(struct rcar_du_vsp *vsp, struct drm_framebuffer *fb,
 			goto fail;
 
 		ret = vsp1_du_map_sg(vsp->vsp, sgt);
-		if (!ret) {
+		if (ret) {
 			sg_free_table(sgt);
-			ret = -ENOMEM;
 			goto fail;
 		}
 	}

drivers/gpu/drm/rockchip/rockchip_drm_gem.c

@@ -36,8 +36,8 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj)
 
 	rk_obj->dma_addr = rk_obj->mm.start;
 
-	ret = iommu_map_sg(private->domain, rk_obj->dma_addr, rk_obj->sgt->sgl,
-			   rk_obj->sgt->nents, prot);
+	ret = iommu_map_sgtable(private->domain, rk_obj->dma_addr, rk_obj->sgt,
+				prot);
 	if (ret < rk_obj->base.size) {
 		DRM_ERROR("failed to map buffer: size=%zd request_size=%zd\n",
 			  ret, rk_obj->base.size);
@@ -98,11 +98,10 @@ static int rockchip_gem_get_pages(struct rockchip_gem_object *rk_obj)
 	 * TODO: Replace this by drm_clflush_sg() once it can be implemented
 	 * without relying on symbols that are not exported.
 	 */
-	for_each_sg(rk_obj->sgt->sgl, s, rk_obj->sgt->nents, i)
+	for_each_sgtable_sg(rk_obj->sgt, s, i)
 		sg_dma_address(s) = sg_phys(s);
 
-	dma_sync_sg_for_device(drm->dev, rk_obj->sgt->sgl, rk_obj->sgt->nents,
-			       DMA_TO_DEVICE);
+	dma_sync_sgtable_for_device(drm->dev, rk_obj->sgt, DMA_TO_DEVICE);
 
 	return 0;
 
@@ -350,8 +349,8 @@ void rockchip_gem_free_object(struct drm_gem_object *obj)
 		if (private->domain) {
 			rockchip_gem_iommu_unmap(rk_obj);
 		} else {
-			dma_unmap_sg(drm->dev, rk_obj->sgt->sgl,
-				     rk_obj->sgt->nents, DMA_BIDIRECTIONAL);
+			dma_unmap_sgtable(drm->dev, rk_obj->sgt,
+					  DMA_BIDIRECTIONAL, 0);
 		}
 		drm_prime_gem_destroy(obj, rk_obj->sgt);
 	} else {
@@ -460,23 +459,6 @@ struct sg_table *rockchip_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	return sgt;
 }
 
-static unsigned long rockchip_sg_get_contiguous_size(struct sg_table *sgt,
-						     int count)
-{
-	struct scatterlist *s;
-	dma_addr_t expected = sg_dma_address(sgt->sgl);
-	unsigned int i;
-	unsigned long size = 0;
-
-	for_each_sg(sgt->sgl, s, count, i) {
-		if (sg_dma_address(s) != expected)
-			break;
-		expected = sg_dma_address(s) + sg_dma_len(s);
-		size += sg_dma_len(s);
-	}
-	return size;
-}
-
 static int
 rockchip_gem_iommu_map_sg(struct drm_device *drm,
 			  struct dma_buf_attachment *attach,
@@ -493,15 +475,13 @@ rockchip_gem_dma_map_sg(struct drm_device *drm,
 			struct sg_table *sg,
 			struct rockchip_gem_object *rk_obj)
 {
-	int count = dma_map_sg(drm->dev, sg->sgl, sg->nents,
-			       DMA_BIDIRECTIONAL);
-	if (!count)
-		return -EINVAL;
+	int err = dma_map_sgtable(drm->dev, sg, DMA_BIDIRECTIONAL, 0);
+	if (err)
+		return err;
 
-	if (rockchip_sg_get_contiguous_size(sg, count) < attach->dmabuf->size) {
+	if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) {
 		DRM_ERROR("failed to map sg_table to contiguous linear address.\n");
-		dma_unmap_sg(drm->dev, sg->sgl, sg->nents,
-			     DMA_BIDIRECTIONAL);
+		dma_unmap_sgtable(drm->dev, sg, DMA_BIDIRECTIONAL, 0);
 		return -EINVAL;
 	}
 

drivers/gpu/drm/tegra/gem.c

@@ -98,8 +98,8 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo,
 		 * the SG table needs to be copied to avoid overwriting any
 		 * other potential users of the original SG table.
 		 */
-		err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, obj->sgt->nents,
-					     GFP_KERNEL);
+		err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl,
+					     obj->sgt->orig_nents, GFP_KERNEL);
 		if (err < 0)
 			goto free;
 	} else {
@@ -196,8 +196,7 @@ static int tegra_bo_iommu_map(struct tegra_drm *tegra, struct tegra_bo *bo)
 
 	bo->iova = bo->mm->start;
 
-	bo->size = iommu_map_sg(tegra->domain, bo->iova, bo->sgt->sgl,
-				bo->sgt->nents, prot);
+	bo->size = iommu_map_sgtable(tegra->domain, bo->iova, bo->sgt, prot);
 	if (!bo->size) {
 		dev_err(tegra->drm->dev, "failed to map buffer\n");
 		err = -ENOMEM;
@@ -264,8 +263,7 @@ static struct tegra_bo *tegra_bo_alloc_object(struct drm_device *drm,
 static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo)
 {
 	if (bo->pages) {
-		dma_unmap_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents,
-			     DMA_FROM_DEVICE);
+		dma_unmap_sgtable(drm->dev, bo->sgt, DMA_FROM_DEVICE, 0);
 		drm_gem_put_pages(&bo->gem, bo->pages, true, true);
 		sg_free_table(bo->sgt);
 		kfree(bo->sgt);
@@ -290,12 +288,9 @@ static int tegra_bo_get_pages(struct drm_device *drm, struct tegra_bo *bo)
 		goto put_pages;
 	}
 
-	err = dma_map_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents,
-			 DMA_FROM_DEVICE);
-	if (err == 0) {
-		err = -EFAULT;
+	err = dma_map_sgtable(drm->dev, bo->sgt, DMA_FROM_DEVICE, 0);
+	if (err)
 		goto free_sgt;
-	}
 
 	return 0;
 
@@ -571,7 +566,7 @@ tegra_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 			goto free;
 	}
 
-	if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0)
+	if (dma_map_sgtable(attach->dev, sgt, dir, 0))
 		goto free;
 
 	return sgt;
@@ -590,7 +585,7 @@ static void tegra_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
 	struct tegra_bo *bo = to_tegra_bo(gem);
 
 	if (bo->pages)
-		dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 
 	sg_free_table(sgt);
 	kfree(sgt);
@@ -609,8 +604,7 @@ static int tegra_gem_prime_begin_cpu_access(struct dma_buf *buf,
 	struct drm_device *drm = gem->dev;
 
 	if (bo->pages)
-		dma_sync_sg_for_cpu(drm->dev, bo->sgt->sgl, bo->sgt->nents,
-				    DMA_FROM_DEVICE);
+		dma_sync_sgtable_for_cpu(drm->dev, bo->sgt, DMA_FROM_DEVICE);
 
 	return 0;
 }
@@ -623,8 +617,7 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf,
 	struct drm_device *drm = gem->dev;
 
 	if (bo->pages)
-		dma_sync_sg_for_device(drm->dev, bo->sgt->sgl, bo->sgt->nents,
-				       DMA_TO_DEVICE);
+		dma_sync_sgtable_for_device(drm->dev, bo->sgt, DMA_TO_DEVICE);
 
 	return 0;
 }

drivers/gpu/drm/tegra/plane.c

@@ -131,12 +131,9 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 		}
 
 		if (sgt) {
-			err = dma_map_sg(dc->dev, sgt->sgl, sgt->nents,
-					 DMA_TO_DEVICE);
-			if (err == 0) {
-				err = -ENOMEM;
+			err = dma_map_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0);
+			if (err)
 				goto unpin;
-			}
 
 			/*
 			 * The display controller needs contiguous memory, so
@@ -144,7 +141,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 			 * map its SG table to a single contiguous chunk of
 			 * I/O virtual memory.
 			 */
-			if (err > 1) {
+			if (sgt->nents > 1) {
 				err = -EINVAL;
 				goto unpin;
 			}
@@ -166,8 +163,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 		struct sg_table *sgt = state->sgt[i];
 
 		if (sgt)
-			dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents,
-				     DMA_TO_DEVICE);
+			dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0);
 
 		host1x_bo_unpin(dc->dev, &bo->base, sgt);
 		state->iova[i] = DMA_MAPPING_ERROR;
@@ -186,8 +182,7 @@ static void tegra_dc_unpin(struct tegra_dc *dc, struct tegra_plane_state *state)
 		struct sg_table *sgt = state->sgt[i];
 
 		if (sgt)
-			dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents,
-				     DMA_TO_DEVICE);
+			dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0);
 
 		host1x_bo_unpin(dc->dev, &bo->base, sgt);
 		state->iova[i] = DMA_MAPPING_ERROR;

drivers/gpu/drm/v3d/v3d_mmu.c

@@ -90,18 +90,17 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo)
 	struct v3d_dev *v3d = to_v3d_dev(shmem_obj->base.dev);
 	u32 page = bo->node.start;
 	u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID;
-	unsigned int count;
-	struct scatterlist *sgl;
+	struct sg_dma_page_iter dma_iter;
 
-	for_each_sg(shmem_obj->sgt->sgl, sgl, shmem_obj->sgt->nents, count) {
-		u32 page_address = sg_dma_address(sgl) >> V3D_MMU_PAGE_SHIFT;
+	for_each_sgtable_dma_page(shmem_obj->sgt, &dma_iter, 0) {
+		dma_addr_t dma_addr = sg_page_iter_dma_address(&dma_iter);
+		u32 page_address = dma_addr >> V3D_MMU_PAGE_SHIFT;
 		u32 pte = page_prot | page_address;
 		u32 i;
 
-		BUG_ON(page_address + (sg_dma_len(sgl) >> V3D_MMU_PAGE_SHIFT) >=
+		BUG_ON(page_address + (PAGE_SIZE >> V3D_MMU_PAGE_SHIFT) >=
 		       BIT(24));
-
-		for (i = 0; i < sg_dma_len(sgl) >> V3D_MMU_PAGE_SHIFT; i++)
+		for (i = 0; i < PAGE_SIZE >> V3D_MMU_PAGE_SHIFT; i++)
 			v3d->pt[page++] = pte + i;
 	}
 

drivers/gpu/drm/virtio/virtgpu_object.c

@@ -72,9 +72,8 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo)
 
 		if (shmem->pages) {
 			if (shmem->mapped) {
-				dma_unmap_sg(vgdev->vdev->dev.parent,
-					     shmem->pages->sgl, shmem->mapped,
-					     DMA_TO_DEVICE);
+				dma_unmap_sgtable(vgdev->vdev->dev.parent,
+					     shmem->pages, DMA_TO_DEVICE, 0);
 				shmem->mapped = 0;
 			}
 
@@ -164,13 +163,13 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 	}
 
 	if (use_dma_api) {
-		shmem->mapped = dma_map_sg(vgdev->vdev->dev.parent,
-					   shmem->pages->sgl,
-					   shmem->pages->nents,
-					   DMA_TO_DEVICE);
-		*nents = shmem->mapped;
+		ret = dma_map_sgtable(vgdev->vdev->dev.parent,
+				      shmem->pages, DMA_TO_DEVICE, 0);
+		if (ret)
+			return ret;
+		*nents = shmem->mapped = shmem->pages->nents;
 	} else {
-		*nents = shmem->pages->nents;
+		*nents = shmem->pages->orig_nents;
 	}
 
 	*ents = kmalloc_array(*nents, sizeof(struct virtio_gpu_mem_entry),
@@ -180,13 +179,20 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 		return -ENOMEM;
 	}
 
-	for_each_sg(shmem->pages->sgl, sg, *nents, si) {
-		(*ents)[si].addr = cpu_to_le64(use_dma_api
-					       ? sg_dma_address(sg)
-					       : sg_phys(sg));
+	if (use_dma_api) {
+		for_each_sgtable_dma_sg(shmem->pages, sg, si) {
+			(*ents)[si].addr = cpu_to_le64(sg_dma_address(sg));
+			(*ents)[si].length = cpu_to_le32(sg_dma_len(sg));
+			(*ents)[si].padding = 0;
+		}
+	} else {
+		for_each_sgtable_sg(shmem->pages, sg, si) {
+			(*ents)[si].addr = cpu_to_le64(sg_phys(sg));
 			(*ents)[si].length = cpu_to_le32(sg->length);
 			(*ents)[si].padding = 0;
 		}
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/virtio/virtgpu_vq.c

@@ -302,7 +302,7 @@ static struct sg_table *vmalloc_to_sgt(char *data, uint32_t size, int *sg_ents)
 		return NULL;
 	}
 
-	for_each_sg(sgt->sgl, sg, *sg_ents, i) {
+	for_each_sgtable_sg(sgt, sg, i) {
 		pg = vmalloc_to_page(data);
 		if (!pg) {
 			sg_free_table(sgt);
@@ -603,9 +603,8 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 
 	if (use_dma_api)
-		dma_sync_sg_for_device(vgdev->vdev->dev.parent,
-				       shmem->pages->sgl, shmem->pages->nents,
-				       DMA_TO_DEVICE);
+		dma_sync_sgtable_for_device(vgdev->vdev->dev.parent,
+					    shmem->pages, DMA_TO_DEVICE);
 
 	cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p));
 	memset(cmd_p, 0, sizeof(*cmd_p));
@@ -1019,9 +1018,8 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 
 	if (use_dma_api)
-		dma_sync_sg_for_device(vgdev->vdev->dev.parent,
-				       shmem->pages->sgl, shmem->pages->nents,
-				       DMA_TO_DEVICE);
+		dma_sync_sgtable_for_device(vgdev->vdev->dev.parent,
+					    shmem->pages, DMA_TO_DEVICE);
 
 	cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p));
 	memset(cmd_p, 0, sizeof(*cmd_p));

drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c

@@ -362,8 +362,7 @@ static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt)
 {
 	struct device *dev = vmw_tt->dev_priv->dev->dev;
 
-	dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents,
-		DMA_BIDIRECTIONAL);
+	dma_unmap_sgtable(dev, &vmw_tt->sgt, DMA_BIDIRECTIONAL, 0);
 	vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents;
 }
 
@@ -383,16 +382,8 @@ static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt)
 static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt)
 {
 	struct device *dev = vmw_tt->dev_priv->dev->dev;
-	int ret;
-
-	ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents,
-			 DMA_BIDIRECTIONAL);
-	if (unlikely(ret == 0))
-		return -ENOMEM;
 
-	vmw_tt->sgt.nents = ret;
-
-	return 0;
+	return dma_map_sgtable(dev, &vmw_tt->sgt, DMA_BIDIRECTIONAL, 0);
 }
 
 /**
@@ -449,10 +440,10 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 		if (unlikely(ret != 0))
 			goto out_sg_alloc_fail;
 
-		if (vsgt->num_pages > vmw_tt->sgt.nents) {
+		if (vsgt->num_pages > vmw_tt->sgt.orig_nents) {
 			uint64_t over_alloc =
 				sgl_size * (vsgt->num_pages -
-					    vmw_tt->sgt.nents);
+					    vmw_tt->sgt.orig_nents);
 
 			ttm_mem_global_free(glob, over_alloc);
 			vmw_tt->sg_alloc_size -= over_alloc;

drivers/gpu/drm/xen/xen_drm_front_gem.c

@@ -217,7 +217,7 @@ xen_drm_front_gem_import_sg_table(struct drm_device *dev,
 		return ERR_PTR(ret);
 
 	DRM_DEBUG("Imported buffer of size %zu with nents %u\n",
-		  size, sgt->nents);
+		  size, sgt->orig_nents);
 
 	return &xen_obj->base;
 }

drivers/gpu/host1x/job.c

@@ -170,11 +170,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 				goto unpin;
 			}
 
-			err = dma_map_sg(dev, sgt->sgl, sgt->nents, dir);
-			if (!err) {
-				err = -ENOMEM;
+			err = dma_map_sgtable(dev, sgt, dir, 0);
+			if (err)
 				goto unpin;
-			}
 
 			job->unpins[job->num_unpins].dev = dev;
 			job->unpins[job->num_unpins].dir = dir;
@@ -228,7 +226,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 		}
 
 		if (host->domain) {
-			for_each_sg(sgt->sgl, sg, sgt->nents, j)
+			for_each_sgtable_sg(sgt, sg, j)
 				gather_size += sg->length;
 			gather_size = iova_align(&host->iova, gather_size);
 
@@ -240,9 +238,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 				goto put;
 			}
 
-			err = iommu_map_sg(host->domain,
+			err = iommu_map_sgtable(host->domain,
 					iova_dma_addr(&host->iova, alloc),
-					sgt->sgl, sgt->nents, IOMMU_READ);
+					sgt, IOMMU_READ);
 			if (err == 0) {
 				__free_iova(&host->iova, alloc);
 				err = -EINVAL;
@@ -252,12 +250,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 			job->unpins[job->num_unpins].size = gather_size;
 			phys_addr = iova_dma_addr(&host->iova, alloc);
 		} else if (sgt) {
-			err = dma_map_sg(host->dev, sgt->sgl, sgt->nents,
-					 DMA_TO_DEVICE);
-			if (!err) {
-				err = -ENOMEM;
+			err = dma_map_sgtable(host->dev, sgt, DMA_TO_DEVICE, 0);
+			if (err)
 				goto put;
-			}
 
 			job->unpins[job->num_unpins].dir = DMA_TO_DEVICE;
 			job->unpins[job->num_unpins].dev = host->dev;
@@ -660,8 +655,7 @@ void host1x_job_unpin(struct host1x_job *job)
 		}
 
 		if (unpin->dev && sgt)
-			dma_unmap_sg(unpin->dev, sgt->sgl, sgt->nents,
-				     unpin->dir);
+			dma_unmap_sgtable(unpin->dev, sgt, unpin->dir, 0);
 
 		host1x_bo_unpin(dev, unpin->bo, sgt);
 		host1x_bo_put(unpin->bo);

drivers/media/platform/vsp1/vsp1_drm.c

@@ -912,8 +912,8 @@ int vsp1_du_map_sg(struct device *dev, struct sg_table *sgt)
 	 * skip cache sync. This will need to be revisited when support for
 	 * non-coherent buffers will be added to the DU driver.
 	 */
-	return dma_map_sg_attrs(vsp1->bus_master, sgt->sgl, sgt->nents,
-				DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	return dma_map_sgtable(vsp1->bus_master, sgt, DMA_TO_DEVICE,
+			       DMA_ATTR_SKIP_CPU_SYNC);
 }
 EXPORT_SYMBOL_GPL(vsp1_du_map_sg);
 
@@ -921,8 +921,8 @@ void vsp1_du_unmap_sg(struct device *dev, struct sg_table *sgt)
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 
-	dma_unmap_sg_attrs(vsp1->bus_master, sgt->sgl, sgt->nents,
-			   DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	dma_unmap_sgtable(vsp1->bus_master, sgt, DMA_TO_DEVICE,
+			  DMA_ATTR_SKIP_CPU_SYNC);
 }
 EXPORT_SYMBOL_GPL(vsp1_du_unmap_sg);
 

drivers/xen/gntdev-dmabuf.c

@@ -247,8 +247,7 @@ static void dmabuf_exp_ops_detach(struct dma_buf *dma_buf,
 
 		if (sgt) {
 			if (gntdev_dmabuf_attach->dir != DMA_NONE)
-				dma_unmap_sg_attrs(attach->dev, sgt->sgl,
-						   sgt->nents,
+				dma_unmap_sgtable(attach->dev, sgt,
 						  gntdev_dmabuf_attach->dir,
 						  DMA_ATTR_SKIP_CPU_SYNC);
 			sg_free_table(sgt);
@@ -288,7 +287,7 @@ dmabuf_exp_ops_map_dma_buf(struct dma_buf_attachment *attach,
 	sgt = dmabuf_pages_to_sgt(gntdev_dmabuf->pages,
 				  gntdev_dmabuf->nr_pages);
 	if (!IS_ERR(sgt)) {
-		if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+		if (dma_map_sgtable(attach->dev, sgt, dir,
 				    DMA_ATTR_SKIP_CPU_SYNC)) {
 			sg_free_table(sgt);
 			kfree(sgt);
@@ -633,7 +632,7 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 
 	/* Now convert sgt to array of pages and check for page validity. */
 	i = 0;
-	for_each_sg_page(sgt->sgl, &sg_iter, sgt->nents, 0) {
+	for_each_sgtable_page(sgt, &sg_iter, 0) {
 		struct page *page = sg_page_iter_page(&sg_iter);
 		/*
 		 * Check if page is valid: this can happen if we are given

include/drm/drm_prime.h

@@ -92,6 +92,8 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags);
 
+unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt);
+
 /* helper functions for importing */
 struct drm_gem_object *drm_gem_prime_import_dev(struct drm_device *dev,
 						struct dma_buf *dma_buf,

samples/vfio-mdev/mbochs.c

@@ -846,7 +846,7 @@ static struct sg_table *mbochs_map_dmabuf(struct dma_buf_attachment *at,
 	if (sg_alloc_table_from_pages(sg, dmabuf->pages, dmabuf->pagecount,
 				      0, dmabuf->mode.size, GFP_KERNEL) < 0)
 		goto err2;
-	if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction))
+	if (dma_map_sgtable(at->dev, sg, direction, 0))
 		goto err3;
 
 	return sg;
@@ -868,6 +868,7 @@ static void mbochs_unmap_dmabuf(struct dma_buf_attachment *at,
 
 	dev_dbg(dev, "%s: %d\n", __func__, dmabuf->id);
 
+	dma_unmap_sgtable(at->dev, sg, direction, 0);
 	sg_free_table(sg);
 	kfree(sg);
 }