[FFmpeg-devel] [RFC PATCH] lavd/v4l2: cover all bufer if bytesperline is set by driver

[Dmitry Buzdyk]

Reminder

On Thu, 2022-11-10 at 01:36 +0600, Dima Buzdyk wrote:
> Some drivers may set bytesperline if hardware use padding bytes for
> alignment. In this case lavd/v4l2 will expect W*H bytes per frame,
> but
> driver will provide Pitch*H bytes which makes v4l2 unhappy.
> 
> This change adjusts frame width to cover entire data buffer aligning
> lavd/v4l2 expectations with data provided by the driver. As a result
> user will be able to get image stream from device, albeit having
> garbage in padding bytes.
> 
> Signed-off-by: Dima Buzdyk <dima.buzdyk at gmail.com>
> ---
>  libavdevice/v4l2.c | 32 +++++++++++++++++++++++++++-----
>  1 file changed, 27 insertions(+), 5 deletions(-)
> 
> diff --git a/libavdevice/v4l2.c b/libavdevice/v4l2.c
> index 5e85d1a2b3..b1e837f740 100644
> --- a/libavdevice/v4l2.c
> +++ b/libavdevice/v4l2.c
> @@ -83,7 +83,7 @@ struct video_data {
>      AVClass *class;
>      int fd;
>      int pixelformat; /* V4L2_PIX_FMT_* */
> -    int width, height;
> +    int width, height, pitch;
>      int frame_size;
>      int interlaced;
>      int top_field_first;
> @@ -202,7 +202,7 @@ fail:
>  }
>  
>  static int device_init(AVFormatContext *ctx, int *width, int
> *height,
> -                       uint32_t pixelformat)
> +                       int *pitch, uint32_t pixelformat)
>  {
>      struct video_data *s = ctx->priv_data;
>      struct v4l2_format fmt = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE
> };
> @@ -224,6 +224,7 @@ static int device_init(AVFormatContext *ctx, int
> *width, int *height,
>                 *width, *height, fmt.fmt.pix.width,
> fmt.fmt.pix.height);
>          *width = fmt.fmt.pix.width;
>          *height = fmt.fmt.pix.height;
> +        *pitch = fmt.fmt.pix.bytesperline;
>      }
>  
>      if (pixelformat != fmt.fmt.pix.pixelformat) {
> @@ -779,6 +780,7 @@ static int device_try_init(AVFormatContext *ctx,
>                             enum AVPixelFormat pix_fmt,
>                             int *width,
>                             int *height,
> +                           int *pitch,
>                             uint32_t *desired_format,
>                             enum AVCodecID *codec_id)
>  {
> @@ -787,7 +789,7 @@ static int device_try_init(AVFormatContext *ctx,
>      *desired_format = ff_fmt_ff2v4l(pix_fmt, ctx->video_codec_id);
>  
>      if (*desired_format) {
> -        ret = device_init(ctx, width, height, *desired_format);
> +        ret = device_init(ctx, width, height, pitch,
> *desired_format);
>          if (ret < 0) {
>              *desired_format = 0;
>              if (ret != AVERROR(EINVAL))
> @@ -804,7 +806,7 @@ static int device_try_init(AVFormatContext *ctx,
>                         (char
> *)av_x_if_null(av_get_pix_fmt_name(ff_fmt_conversion_table[i].ff_fmt)
> , "none"));
>  
>                  *desired_format =
> ff_fmt_conversion_table[i].v4l2_fmt;
> -                ret = device_init(ctx, width, height,
> *desired_format);
> +                ret = device_init(ctx, width, height, pitch,
> *desired_format);
>                  if (ret >= 0)
>                      break;
>                  else if (ret != AVERROR(EINVAL))
> @@ -933,11 +935,13 @@ static int v4l2_read_header(AVFormatContext
> *ctx)
>  
>          s->width  = fmt.fmt.pix.width;
>          s->height = fmt.fmt.pix.height;
> +        s->pitch  = fmt.fmt.pix.bytesperline;
>          av_log(ctx, AV_LOG_VERBOSE,
>                 "Setting frame size to %dx%d\n", s->width, s-
> >height);
>      }
>  
> -    res = device_try_init(ctx, pix_fmt, &s->width, &s->height,
> &desired_format, &codec_id);
> +    res = device_try_init(ctx, pix_fmt, &s->width, &s->height, &s-
> >pitch,
> +                          &desired_format, &codec_id);
>      if (res < 0)
>          goto fail;
>  
> @@ -948,6 +952,24 @@ static int v4l2_read_header(AVFormatContext
> *ctx)
>      if (codec_id != AV_CODEC_ID_NONE && ctx->video_codec_id ==
> AV_CODEC_ID_NONE)
>          ctx->video_codec_id = codec_id;
>  
> +    /* If bytesperpixel is set by driver then set width co cover
> full
> +     * buffer area even if there are garbage data to be displayed.
> +     * It is better to display padding bytes and give application
> ability
> +     * to crop image later than fail to display image stream
> completely */
> +    if (s->pitch) {
> +        int linesize;
> +
> +        pix_fmt = ff_fmt_v4l2ff(desired_format, codec_id);
> +        linesize = av_image_get_linesize(pix_fmt, s->width, 0);
> +        if (linesize > 0) {
> +            s->width = s->pitch * s->width / linesize;
> +
> +            av_log(ctx, AV_LOG_INFO,
> +                   "Expand frame width to %dx%d to cover full
> buffer\n",
> +                   s->width, s->height);
> +        }
> +    }
> +
>      if ((res = av_image_check_size(s->width, s->height, 0, ctx)) <
> 0)
>          goto fail;
>