Hi, Houlong:

Some inline comment.

On Wed, 2018-06-27 at 19:16 +0800, Houlong Wei wrote:

[...]

+
+int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u32 event)
+{
+	u32 arg_b;
+
+	if (event >= CMDQ_MAX_EVENT || event < 0)

The type of event is 'u32', so checking 'event < 0' is redundant.

+		return -EINVAL;
+
+	/*
+	 * WFE arg_b
+	 * bit 0-11: wait value
+	 * bit 15: 1 - wait, 0 - no wait
+	 * bit 16-27: update value
+	 * bit 31: 1 - update, 0 - no update
+	 */
+	arg_b = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
+
+	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WFE, event, arg_b);
+}
+EXPORT_SYMBOL(cmdq_pkt_wfe);
+
+int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u32 event)
+{
+	if (event >= CMDQ_MAX_EVENT || event < 0)

The type of event is 'u32', so checking 'event < 0' is redundant.

+		return -EINVAL;
+
+	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WFE, event,
+				       CMDQ_WFE_UPDATE);
+}
+EXPORT_SYMBOL(cmdq_pkt_clear_event);
+
+static int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
+{
+	int err;
+
+	if (cmdq_pkt_is_finalized(pkt))
+		return 0;
+
+	/* insert EOC and generate IRQ for each command iteration */
+	err = cmdq_pkt_append_command(pkt, CMDQ_CODE_EOC, 0, CMDQ_EOC_IRQ_EN);
+	if (err < 0)
+		return err;
+
+	/* JUMP to end */
+	err = cmdq_pkt_append_command(pkt, CMDQ_CODE_JUMP, 0, CMDQ_JUMP_PASS);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+int cmdq_pkt_flush_async(struct cmdq_client *client, struct cmdq_pkt *pkt,
+			 cmdq_async_flush_cb cb, void *data)
+{
+	int err;
+	struct device *dev;
+	dma_addr_t dma_addr;
+
+	err = cmdq_pkt_finalize(pkt);
+	if (err < 0)
+		return err;
+
+	dev = client->chan->mbox->dev;
+	dma_addr = dma_map_single(dev, pkt->va_base, pkt->cmd_buf_size,
+		DMA_TO_DEVICE);

You map here, but I could not find unmap, so the unmap should be done in
client driver. I would prefer a symmetric map/unmap which means that
both map and unmap are done in client driver. I think you put map here
because you should map after finalize. Therefore, export
cmdq_pkt_finalize() to client driver and let client do finalize, so
there is no finalize in flush function. This method have a benefit that
if client reuse command buffer, it need not to map/unmap frequently.

Regards,
CK

+	if (dma_mapping_error(dev, dma_addr)) {
+		dev_err(client->chan->mbox->dev, "dma map failed\n");
+		return -ENOMEM;
+	}
+
+	pkt->pa_base = dma_addr;
+	pkt->cb.cb = cb;
+	pkt->cb.data = data;
+
+	mbox_send_message(client->chan, pkt);
+	/* We can send next packet immediately, so just call txdone. */
+	mbox_client_txdone(client->chan, 0);
+
+	return 0;
+}
+EXPORT_SYMBOL(cmdq_pkt_flush_async);
+
+struct cmdq_flush_completion {
+	struct completion cmplt;
+	bool err;
+};
+
+static void cmdq_pkt_flush_cb(struct cmdq_cb_data data)
+{
+	struct cmdq_flush_completion *cmplt = data.data;
+
+	cmplt->err = data.err;
+	complete(&cmplt->cmplt);
+}
+
+int cmdq_pkt_flush(struct cmdq_client *client, struct cmdq_pkt *pkt)
+{
+	struct cmdq_flush_completion cmplt;
+	int err;
+
+	init_completion(&cmplt.cmplt);
+	err = cmdq_pkt_flush_async(client, pkt, cmdq_pkt_flush_cb, &cmplt);
+	if (err < 0)
+		return err;
+	wait_for_completion(&cmplt.cmplt);
+
+	return cmplt.err ? -EFAULT : 0;
+}
+EXPORT_SYMBOL(cmdq_pkt_flush);

[...]