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

@@ -140,21 +140,20 @@ 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;
 }
 
 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)
@@ -395,30 +395,26 @@ 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))
 			goto free_sgt;
 
 		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 */
@@ -432,8 +428,9 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 	return sgt;
 
  release:
-	for_each_sg(sgt->sgl, sg, num, i)
-		put_page(sg_page(sg));
+	for_each_sgtable_sg(sgt, sg, i)
+		if (sg_page(sg))
+			put_page(sg_page(sg));
  free_table:
 	sg_free_table(sgt);
  free_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

@@ -471,26 +471,9 @@ 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)
-				return ERR_PTR(-EINVAL);
-
-			next_addr = sg_dma_address(s) + sg_dma_len(s);
-		}
-	}
+	/* check if the entries in the sg_table are contiguous */
+	if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size)
+		return ERR_PTR(-EINVAL);
 
 	/* Create a CMA GEM buffer. */
 	cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size);

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 */
@@ -404,9 +404,8 @@ 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,
-				    etnaviv_op_to_dma_dir(op));
+		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;
 	}