drm/panfrost: Provide a custom dma_buf implementation

Before we introduce cached CPU mappings, we want a dma_buf
implementation satisfying synchronization requests around CPU
accesses coming from a dma_buf exported by our driver. Let's
provide our own implementation relying on the default
gem_shmem_prime helpers designed for that purpose.

v5:
- New patch

v6:
- Collect R-b

v7:
- Hand-roll our own dma_buf boilerplate

v8:
- No changes

Reviewed-by: Steven Price <steven.price@arm.com>
Link: https://patch.msgid.link/20251208100841.730527-9-boris.brezillon@collabora.com
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>

drivers/gpu/drm/panfrost/panfrost_drv.c

@@ -852,6 +852,7 @@ static const struct drm_driver panfrost_drm_driver = {
 	.minor			= 5,
 
 	.gem_create_object	= panfrost_gem_create_object,
+	.gem_prime_import	= panfrost_gem_prime_import,
 	.gem_prime_import_sg_table = panfrost_gem_prime_import_sg_table,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init = panfrost_debugfs_init,

drivers/gpu/drm/panfrost/panfrost_gem.c

@@ -277,6 +277,128 @@ static size_t panfrost_gem_rss(struct drm_gem_object *obj)
 	return 0;
 }
 
+static struct sg_table *
+panfrost_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
+			       enum dma_data_direction dir)
+{
+	struct sg_table *sgt = drm_gem_map_dma_buf(attach, dir);
+
+	if (!IS_ERR(sgt))
+		attach->priv = sgt;
+
+	return sgt;
+}
+
+static void
+panfrost_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
+				 struct sg_table *sgt,
+				 enum dma_data_direction dir)
+{
+	attach->priv = NULL;
+	drm_gem_unmap_dma_buf(attach, sgt, dir);
+}
+
+static int
+panfrost_gem_prime_begin_cpu_access(struct dma_buf *dma_buf,
+				    enum dma_data_direction dir)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct drm_device *dev = obj->dev;
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+	struct dma_buf_attachment *attach;
+
+	dma_resv_lock(obj->resv, NULL);
+	if (shmem->sgt)
+		dma_sync_sgtable_for_cpu(dev->dev, shmem->sgt, dir);
+
+	if (shmem->vaddr)
+		invalidate_kernel_vmap_range(shmem->vaddr, shmem->base.size);
+
+	list_for_each_entry(attach, &dma_buf->attachments, node) {
+		struct sg_table *sgt = attach->priv;
+
+		if (sgt)
+			dma_sync_sgtable_for_cpu(attach->dev, sgt, dir);
+	}
+	dma_resv_unlock(obj->resv);
+
+	return 0;
+}
+
+static int
+panfrost_gem_prime_end_cpu_access(struct dma_buf *dma_buf,
+				  enum dma_data_direction dir)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct drm_device *dev = obj->dev;
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+	struct dma_buf_attachment *attach;
+
+	dma_resv_lock(obj->resv, NULL);
+	list_for_each_entry(attach, &dma_buf->attachments, node) {
+		struct sg_table *sgt = attach->priv;
+
+		if (sgt)
+			dma_sync_sgtable_for_device(attach->dev, sgt, dir);
+	}
+
+	if (shmem->vaddr)
+		flush_kernel_vmap_range(shmem->vaddr, shmem->base.size);
+
+	if (shmem->sgt)
+		dma_sync_sgtable_for_device(dev->dev, shmem->sgt, dir);
+
+	dma_resv_unlock(obj->resv);
+	return 0;
+}
+
+static const struct dma_buf_ops panfrost_dma_buf_ops = {
+	.attach = drm_gem_map_attach,
+	.detach = drm_gem_map_detach,
+	.map_dma_buf = panfrost_gem_prime_map_dma_buf,
+	.unmap_dma_buf = panfrost_gem_prime_unmap_dma_buf,
+	.release = drm_gem_dmabuf_release,
+	.mmap = drm_gem_dmabuf_mmap,
+	.vmap = drm_gem_dmabuf_vmap,
+	.vunmap = drm_gem_dmabuf_vunmap,
+	.begin_cpu_access = panfrost_gem_prime_begin_cpu_access,
+	.end_cpu_access = panfrost_gem_prime_end_cpu_access,
+};
+
+static struct dma_buf *
+panfrost_gem_prime_export(struct drm_gem_object *obj, int flags)
+{
+	struct drm_device *dev = obj->dev;
+	struct dma_buf_export_info exp_info = {
+		.exp_name = KBUILD_MODNAME,
+		.owner = THIS_MODULE,
+		.ops = &panfrost_dma_buf_ops,
+		.size = obj->size,
+		.flags = flags,
+		.priv = obj,
+		.resv = obj->resv,
+	};
+
+	return drm_gem_dmabuf_export(dev, &exp_info);
+}
+
+struct drm_gem_object *
+panfrost_gem_prime_import(struct drm_device *dev,
+			  struct dma_buf *dma_buf)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+
+	if (dma_buf->ops == &panfrost_dma_buf_ops && obj->dev == dev) {
+		/* Importing dmabuf exported from our own gem increases
+		 * refcount on gem itself instead of f_count of dmabuf.
+		 */
+		drm_gem_object_get(obj);
+		return obj;
+	}
+
+	return drm_gem_prime_import(dev, dma_buf);
+}
+
 static const struct drm_gem_object_funcs panfrost_gem_funcs = {
 	.free = panfrost_gem_free_object,
 	.open = panfrost_gem_open,
@@ -285,6 +407,7 @@ static const struct drm_gem_object_funcs panfrost_gem_funcs = {
 	.pin = panfrost_gem_pin,
 	.unpin = drm_gem_shmem_object_unpin,
 	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.export = panfrost_gem_prime_export,
 	.vmap = drm_gem_shmem_object_vmap,
 	.vunmap = drm_gem_shmem_object_vunmap,
 	.mmap = drm_gem_shmem_object_mmap,

drivers/gpu/drm/panfrost/panfrost_gem.h

@@ -132,6 +132,9 @@ struct drm_gem_object *
 panfrost_gem_prime_import_sg_table(struct drm_device *dev,
 				   struct dma_buf_attachment *attach,
 				   struct sg_table *sgt);
+struct drm_gem_object *
+panfrost_gem_prime_import(struct drm_device *dev,
+			  struct dma_buf *dma_buf);
 
 struct panfrost_gem_object *
 panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags);