[PATCH v1, 07/14] media: mtk-vcodec: Add msg queue feature for lat and core architecture

[Tzung-Bi Shih]

On Wed, Jul 7, 2021 at 2:22 PM Yunfei Dong <yunfei.dong at mediatek.com> wrote:
> @@ -464,6 +469,11 @@ struct mtk_vcodec_enc_pdata {
>   * comp_dev: component hardware device
>   * component_node: component node
>   * comp_idx: component index
> + *
> + * core_read: Wait queue used to signalize when core get useful lat buffer
> + * core_queue: List of V4L2 lat_buf
To be neat, replace "Wait" to "wait" and "List" to "list".

> +int vdec_msg_queue_init(
> +       struct mtk_vcodec_ctx *ctx,
> +       struct vdec_msg_queue *msg_queue,
> +       core_decode_cb_t core_decode,
> +       int private_size)
> +{
> +       struct vdec_lat_buf *lat_buf;
> +       int i, err;
> +
> +       init_waitqueue_head(&msg_queue->lat_read);
> +       INIT_LIST_HEAD(&msg_queue->lat_queue);
> +       spin_lock_init(&msg_queue->lat_lock);
> +       msg_queue->num_lat = 0;
> +
> +       msg_queue->wdma_addr.size = vde_msg_queue_get_trans_size(
> +               ctx->picinfo.buf_w, ctx->picinfo.buf_h);
> +
> +       err = mtk_vcodec_mem_alloc(ctx, &msg_queue->wdma_addr);
> +       if (err) {
> +               mtk_v4l2_err("failed to allocate wdma_addr buf");
> +               return -ENOMEM;
> +       }
> +       msg_queue->wdma_rptr_addr = msg_queue->wdma_addr.dma_addr;
> +       msg_queue->wdma_wptr_addr = msg_queue->wdma_addr.dma_addr;
> +
> +       for (i = 0; i < NUM_BUFFER_COUNT; i++) {
> +               lat_buf = &msg_queue->lat_buf[i];
> +
> +               lat_buf->wdma_err_addr.size = VDEC_ERR_MAP_SZ_AVC;
> +               err = mtk_vcodec_mem_alloc(ctx, &lat_buf->wdma_err_addr);
> +               if (err) {
> +                       mtk_v4l2_err("failed to allocate wdma_err_addr buf[%d]", i);
> +                       return -ENOMEM;
> +               }
> +
> +               lat_buf->slice_bc_addr.size = VDEC_LAT_SLICE_HEADER_SZ;
> +               err = mtk_vcodec_mem_alloc(ctx, &lat_buf->slice_bc_addr);
> +               if (err) {
> +                       mtk_v4l2_err("failed to allocate wdma_addr buf[%d]", i);
> +                       return -ENOMEM;
> +               }
> +
> +               lat_buf->private_data = kzalloc(private_size, GFP_KERNEL);
> +               if (!lat_buf->private_data) {
> +                       mtk_v4l2_err("failed to allocate private_data[%d]", i);
> +                       return -ENOMEM;
> +               }
> +
> +               lat_buf->ctx = ctx;
> +               lat_buf->core_decode = core_decode;
> +               vdec_msg_queue_buf_to_lat(lat_buf);
> +       }
Doesn't it need to call mtk_vcodec_mem_free() and kfree() for any failure paths?

> +struct vdec_lat_buf *vdec_msg_queue_get_core_buf(
> +       struct mtk_vcodec_dev *dev)
> +{
> +       struct vdec_lat_buf *buf;
> +       int ret;
> +
> +       spin_lock(&dev->core_lock);
> +       if (list_empty(&dev->core_queue)) {
> +               mtk_v4l2_debug(3, "core queue is NULL, num_core = %d", dev->num_core);
> +               spin_unlock(&dev->core_lock);
> +               ret = wait_event_freezable(dev->core_read,
> +                       !list_empty(&dev->core_queue));
> +               if (ret)
> +                       return NULL;
Should be !ret?

> +void vdec_msg_queue_buf_to_core(struct mtk_vcodec_dev *dev,
> +       struct vdec_lat_buf *buf)
> +{
> +       spin_lock(&dev->core_lock);
> +       list_add_tail(&buf->core_list, &dev->core_queue);
> +       dev->num_core++;
> +       wake_up_all(&dev->core_read);
> +       mtk_v4l2_debug(3, "queu buf addr: (0x%p)", buf);
Typo.

> +bool vdec_msg_queue_wait_lat_buf_full(struct vdec_msg_queue *msg_queue)
> +{
> +       long timeout_jiff;
> +       int ret, i;
> +
> +       for (i = 0; i < NUM_BUFFER_COUNT + 2; i++) {
> +              timeout_jiff = msecs_to_jiffies(1000);
> +              ret = wait_event_timeout(msg_queue->lat_read,
> +                    msg_queue->num_lat == NUM_BUFFER_COUNT, timeout_jiff);
> +              if (ret) {
> +                     mtk_v4l2_debug(3, "success to get lat buf: %d",
> +                            msg_queue->num_lat);
> +                     return true;
> +              }
> +       }
Why does it need the loop?  i is unused.

> +void vdec_msg_queue_deinit(
> +       struct mtk_vcodec_ctx *ctx,
> +       struct vdec_msg_queue *msg_queue)
> +{
> +       struct vdec_lat_buf *lat_buf;
> +       struct mtk_vcodec_mem *mem;
> +       int i;
> +
> +       mem = &msg_queue->wdma_addr;
> +       if (mem->va)
> +               mtk_vcodec_mem_free(ctx, mem);
> +       for (i = 0; i < NUM_BUFFER_COUNT; i++) {
> +               lat_buf = &msg_queue->lat_buf[i];
> +
> +               mem = &lat_buf->wdma_err_addr;
> +               if (mem->va)
> +                       mtk_vcodec_mem_free(ctx, mem);
> +
> +               mem = &lat_buf->slice_bc_addr;
> +               if (mem->va)
> +                       mtk_vcodec_mem_free(ctx, mem);
> +
> +               if (lat_buf->private_data)
> +                       kfree(lat_buf->private_data);
> +       }
> +
> +       msg_queue->init_done = false;
Have no idea what init_done does in the code.  It is not included in
any branch condition.

> +/**
> + * vdec_msg_queue_init - init lat buffer information.
> + * @ctx: v4l2 ctx
> + * @msg_queue: used to store the lat buffer information
> + * @core_decode: core decode callback for each codec
> + * @private_size: the private data size used to share with core
> + */
> +int vdec_msg_queue_init(
> +       struct mtk_vcodec_ctx *ctx,
> +       struct vdec_msg_queue *msg_queue,
> +       core_decode_cb_t core_decode,
> +       int private_size);
Would prefer to have *msg_queue as the first argument (also applies to
all operators of vdec_msg_queue).

> +/**
> + * vdec_msg_queue_get_core_buf - get used core buffer for lat decode.
> + * @dev: mtk vcodec device
> + */
> +struct vdec_lat_buf *vdec_msg_queue_get_core_buf(
> +       struct mtk_vcodec_dev *dev);
This is weird: vdec_msg_queue's operator but manipulating mtk_vcodec_dev?

> +
> +/**
> + * vdec_msg_queue_buf_to_core - queue buf to the core for core decode.
> + * @dev: mtk vcodec device
> + * @buf: current lat buffer
> + */
> +void vdec_msg_queue_buf_to_core(struct mtk_vcodec_dev *dev,
> +       struct vdec_lat_buf *buf);
Also weird.

> +/**
> + * vdec_msg_queue_buf_to_lat - queue buf to lat for lat decode.
> + * @buf: current lat buffer
> + */
> +void vdec_msg_queue_buf_to_lat(struct vdec_lat_buf *buf);
It should at least accept a struct vdec_msg_queue argument (or which
msg queue should the buf put into?).

> +/**
> + * vdec_msg_queue_update_ube_rptr - used to updata the ube read point.
Typo.

> +/**
> + * vdec_msg_queue_update_ube_wptr - used to updata the ube write point.
Typo.

> +/**
> + * vdec_msg_queue_deinit - deinit lat buffer information.
> + * @ctx: v4l2 ctx
> + * @msg_queue: used to store the lat buffer information
> + */
> +void vdec_msg_queue_deinit(
> +       struct mtk_vcodec_ctx *ctx,
> +       struct vdec_msg_queue *msg_queue);
Would prefer to have *msg_queue as the first argument.


The position of struct vdec_msg_queue is weird.  It looks like the msg
queue is only for struct vdec_lat_buf.  If so, would vdec_msg_queue be
better to call vdec_lat_queue or something similar?

It shouldn't touch the core queue in mtk_vcodec_dev anyway.  Is it
possible to generalize the queue-related code for both lat and core
queues?