[PATCH v2 1/3] media: videobuf2: add opt-in DMA-BUF CPU access

[Karl Mehltretter <kmehltretter@gmail.com>]

Drivers that transfer buffer contents with the CPU must bracket access to
imported DMA-BUFs with dma_buf_begin_cpu_access() and
dma_buf_end_cpu_access().

Add a uses_cpu_access queue flag for vb2-vmalloc queues to bracket the
interval from buf_prepare() through buf_finish(), using read access for
output queues and write access for capture queues.

Keep this opt-in because some vb2-vmalloc drivers pass imported buffers to
hardware, and end access in process context because DMA-BUF callbacks may
sleep and return errors.

Signed-off-by: Karl Mehltretter <kmehltretter@gmail.com>
---
v2:
- Scope uses_cpu_access to vb2-vmalloc queues and drop the attach_dmabuf
  dma_dir parameter from vb2_mem_ops and the allocators (Tomasz Figa).
- Call __vb2_buf_end_cpu_access() from __vb2_buf_cancel() (Tomasz Figa).

 .../media/common/videobuf2/videobuf2-core.c   | 76 +++++++++++++++++++
 include/media/videobuf2-core.h                |  5 ++
 2 files changed, 81 insertions(+)

diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index 29e539ee002e..6c32d3cccb93 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -371,6 +371,65 @@ static void __vb2_buf_mem_finish(struct vb2_buffer *vb)
 		call_void_memop(vb, finish, vb->planes[plane].mem_priv);
 }
 
+/* Output buffers are read by the driver; capture buffers are written. */
+static enum dma_data_direction vb2_cpu_access_dir(const struct vb2_queue *q)
+{
+	return q->is_output ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+}
+
+static bool __vb2_dmabuf_is_duplicate(const struct vb2_buffer *vb,
+				      unsigned int plane)
+{
+	unsigned int i;
+
+	for (i = 0; i < plane; i++)
+		if (vb->planes[i].dbuf == vb->planes[plane].dbuf)
+			return true;
+
+	return false;
+}
+
+static void __vb2_buf_end_cpu_access(struct vb2_buffer *vb,
+				     unsigned int num_planes)
+{
+	struct vb2_queue *q = vb->vb2_queue;
+	enum dma_data_direction dir = vb2_cpu_access_dir(q);
+	unsigned int plane;
+
+	for (plane = 0; plane < num_planes; plane++) {
+		int ret;
+
+		if (__vb2_dmabuf_is_duplicate(vb, plane))
+			continue;
+
+		ret = dma_buf_end_cpu_access(vb->planes[plane].dbuf, dir);
+		if (ret)
+			pr_warn_ratelimited("[%s] failed to end CPU access to dmabuf plane %u: %d\n",
+					    q->name, plane, ret);
+	}
+}
+
+static int __vb2_buf_begin_cpu_access(struct vb2_buffer *vb)
+{
+	struct vb2_queue *q = vb->vb2_queue;
+	enum dma_data_direction dir = vb2_cpu_access_dir(q);
+	unsigned int plane;
+	int ret;
+
+	for (plane = 0; plane < vb->num_planes; plane++) {
+		if (__vb2_dmabuf_is_duplicate(vb, plane))
+			continue;
+
+		ret = dma_buf_begin_cpu_access(vb->planes[plane].dbuf, dir);
+		if (ret) {
+			__vb2_buf_end_cpu_access(vb, plane);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * __setup_offsets() - setup unique offsets ("cookies") for every plane in
  * the buffer.
@@ -1504,9 +1563,21 @@ static int __prepare_dmabuf(struct vb2_buffer *vb)
 		}
 	}
 
+	if (q->uses_cpu_access) {
+		ret = __vb2_buf_begin_cpu_access(vb);
+		if (ret) {
+			dprintk(q, 1, "failed to begin CPU access to dmabuf: %d\n",
+				ret);
+			call_void_vb_qop(vb, buf_cleanup, vb);
+			goto err_put_vb2_buf;
+		}
+	}
+
 	ret = call_vb_qop(vb, buf_prepare, vb);
 	if (ret) {
 		dprintk(q, 1, "buffer preparation failed\n");
+		if (q->uses_cpu_access)
+			__vb2_buf_end_cpu_access(vb, vb->num_planes);
 		call_void_vb_qop(vb, buf_cleanup, vb);
 		goto err_put_vb2_buf;
 	}
@@ -1720,6 +1791,7 @@ EXPORT_SYMBOL_GPL(vb2_core_prepare_buf);
 static void __vb2_buf_cancel(struct vb2_buffer *vb)
 {
 	struct media_request *req = vb->req_obj.req;
+	struct vb2_queue *q = vb->vb2_queue;
 
 	/*
 	 * If a request is associated with this buffer, then
@@ -1743,6 +1815,8 @@ static void __vb2_buf_cancel(struct vb2_buffer *vb)
 
 	if (vb->prepared) {
 		call_void_vb_qop(vb, buf_finish, vb);
+		if (q->memory == VB2_MEMORY_DMABUF && q->uses_cpu_access)
+			__vb2_buf_end_cpu_access(vb, vb->num_planes);
 		vb->prepared = 0;
 	}
 	__vb2_dqbuf(vb);
@@ -2191,6 +2265,8 @@ int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb,
 	}
 
 	call_void_vb_qop(vb, buf_finish, vb);
+	if (q->memory == VB2_MEMORY_DMABUF && q->uses_cpu_access)
+		__vb2_buf_end_cpu_access(vb, vb->num_planes);
 	vb->prepared = 0;
 
 	if (pindex)
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 4b4f4c15c53a..bbcdd8c8989a 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -510,6 +510,10 @@ struct vb2_buf_ops {
  *		->finish().
  * @non_coherent_mem: when set queue will attempt to allocate buffers using
  *		non-coherent memory.
+ * @uses_cpu_access: the driver transfers buffer data with the CPU instead of
+ *		DMA. For imported dma-bufs on vb2-vmalloc queues, videobuf2
+ *		brackets the interval from buf_prepare through buf_finish with
+ *		dma_buf_begin_cpu_access() and dma_buf_end_cpu_access().
  * @lock:	pointer to a mutex that protects the &struct vb2_queue. The
  *		driver must set this to a mutex to let the v4l2 core serialize
  *		the queuing ioctls. This lock is used when waiting for a new
@@ -614,6 +618,7 @@ struct vb2_queue {
 	unsigned int			uses_requests:1;
 	unsigned int			allow_cache_hints:1;
 	unsigned int			non_coherent_mem:1;
+	unsigned int			uses_cpu_access:1;
 
 	struct mutex			*lock;
 	void				*owner;
-- 
2.39.5 (Apple Git-154)