[PATCH/RFC v1.1] drm: rcar-du: Allow importing non-contiguous dma-buf with VSP

[Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>]

When the DU sources its frames from a VSP, it performs no memory access
and thus has no requirements on imported dma-buf memory types. In
particular the DU could import a physically non-contiguous buffer that
would later be mapped contiguously through the VSP IOMMU.

This use case isn't supported at the moment as the GEM CMA helpers will
reject any non-contiguous buffer, and the DU isn't connected to an IOMMU
that can make the buffer contiguous for DMA. Fix this by implementing a
custom .gem_prime_import_sg_table() operation that accepts all imported
dma-buf regardless of the number of scatterlist entries.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
Changes since v1:

- Duplicate the imported scatter gather table in
  rcar_du_vsp_plane_prepare_fb()

This patch fixes a bug of the previous version and is posted in case anyone
would like to test the implementation. I still plan to give Noralf's GEM
library a try as an alternative approach to this series.

 drivers/gpu/drm/rcar-du/rcar_du_drv.c |  2 +-
 drivers/gpu/drm/rcar-du/rcar_du_kms.c | 39 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/rcar-du/rcar_du_kms.h |  7 +++++++
 drivers/gpu/drm/rcar-du/rcar_du_vsp.c | 34 ++++++++++++++++++++++++++----
 4 files changed, 77 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index 48c166f925a3..d999231f98c7 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -289,7 +289,7 @@ static struct drm_driver rcar_du_driver = {
 	.gem_prime_import	= drm_gem_prime_import,
 	.gem_prime_export	= drm_gem_prime_export,
 	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
-	.gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table,
+	.gem_prime_import_sg_table = rcar_du_gem_prime_import_sg_table,
 	.gem_prime_vmap		= drm_gem_cma_prime_vmap,
 	.gem_prime_vunmap	= drm_gem_cma_prime_vunmap,
 	.gem_prime_mmap		= drm_gem_cma_prime_mmap,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 566d1a948c8f..2dd0c2ba047d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -20,6 +20,7 @@
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 
+#include <linux/dma-buf.h>
 #include <linux/of_graph.h>
 #include <linux/wait.h>
 
@@ -148,6 +149,44 @@ const struct rcar_du_format_info *rcar_du_format_info(u32 fourcc)
  * Frame buffer
  */
 
+struct drm_gem_object *rcar_du_gem_prime_import_sg_table(struct drm_device *dev,
+				struct dma_buf_attachment *attach,
+				struct sg_table *sgt)
+{
+	struct rcar_du_device *rcdu = dev->dev_private;
+	struct drm_gem_cma_object *cma_obj;
+	struct drm_gem_object *gem_obj;
+	int ret;
+
+	if (!rcar_du_has(rcdu, RCAR_DU_FEATURE_VSP1_SOURCE))
+		return drm_gem_cma_prime_import_sg_table(dev, attach, sgt);
+
+	/* Create a CMA GEM buffer. */
+	cma_obj = kzalloc(sizeof(*cma_obj), GFP_KERNEL);
+	if (!cma_obj)
+		return ERR_PTR(-ENOMEM);
+	gem_obj = &cma_obj->base;
+
+	ret = drm_gem_object_init(dev, gem_obj, attach->dmabuf->size);
+	if (ret)
+		goto error;
+
+	ret = drm_gem_create_mmap_offset(gem_obj);
+	if (ret) {
+		drm_gem_object_release(gem_obj);
+		goto error;
+	}
+
+	cma_obj->paddr = 0;
+	cma_obj->sgt = sgt;
+
+	return gem_obj;
+
+error:
+	kfree(cma_obj);
+	return ERR_PTR(ret);
+}
+
 int rcar_du_dumb_create(struct drm_file *file, struct drm_device *dev,
 			struct drm_mode_create_dumb *args)
 {
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.h b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
index 07951d5fe38b..10b2bb0f0df9 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
@@ -16,10 +16,13 @@
 
 #include <linux/types.h>
 
+struct dma_buf_attachment;
 struct drm_file;
 struct drm_device;
+struct drm_gem_object;
 struct drm_mode_create_dumb;
 struct rcar_du_device;
+struct sg_table;
 
 struct rcar_du_format_info {
 	u32 fourcc;
@@ -36,4 +39,8 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu);
 int rcar_du_dumb_create(struct drm_file *file, struct drm_device *dev,
 			struct drm_mode_create_dumb *args);
 
+struct drm_gem_object *rcar_du_gem_prime_import_sg_table(struct drm_device *dev,
+				struct dma_buf_attachment *attach,
+				struct sg_table *sgt);
+
 #endif /* __RCAR_DU_KMS_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index 2c260c33840b..73fdc814aa39 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -224,10 +224,36 @@ static int rcar_du_vsp_plane_prepare_fb(struct drm_plane *plane,
 			drm_fb_cma_get_gem_obj(state->fb, i);
 		struct sg_table *sgt = &rstate->sg_tables[i];
 
-		ret = dma_get_sgtable(rcdu->dev, sgt, gem->vaddr, gem->paddr,
-				      gem->base.size);
-		if (ret)
-			goto fail;
+		if (gem->sgt) {
+			struct scatterlist *src;
+			struct scatterlist *dst;
+
+			/*
+			 * If the GEM buffer has a scatter gather table, it has
+			 * been imported from a dma-buf and has no physical
+			 * address as it might not be physically contiguous.
+			 * Copy the original scatter gather table to map it to
+			 * the VSP.
+			 */
+			ret = sg_alloc_table(sgt, gem->sgt->orig_nents,
+					     GFP_KERNEL);
+			if (ret)
+				goto fail;
+
+			src = gem->sgt->sgl;
+			dst = sgt->sgl;
+			for (i = 0; i < gem->sgt->orig_nents; ++i) {
+				sg_set_page(dst, sg_page(src), src->length,
+					    src->offset);
+				src = sg_next(src);
+				dst = sg_next(dst);
+			}
+		} else {
+			ret = dma_get_sgtable(rcdu->dev, sgt, gem->vaddr,
+					      gem->paddr, gem->base.size);
+			if (ret)
+				goto fail;
+		}
 
 		ret = vsp1_du_map_sg(vsp->vsp, sgt);
 		if (!ret) {
-- 
Regards,

Laurent Pinchart