[FFmpeg-devel] [PATCH] avformat/mov: Fix get_eia608_packet c608 caption reformatting

[Andreas Rheinhardt]

Pavel Koshevoy:
> ---
>  libavformat/mov.c | 40 +++++++++++++++++++++++++++++++---------
>  1 file changed, 31 insertions(+), 9 deletions(-)
> 
> diff --git a/libavformat/mov.c b/libavformat/mov.c
> index 85aef33b19..422e515fe8 100644
> --- a/libavformat/mov.c
> +++ b/libavformat/mov.c
> @@ -10790,22 +10790,44 @@ static int mov_change_extradata(AVStream *st, AVPacket *pkt)
>  
>  static int get_eia608_packet(AVIOContext *pb, AVPacket *pkt, int size)
>  {
> -    int new_size, ret;
> -
> +    /* We can't make assumptions about the structure of the payload,
> +       because it may include multiple cdat and cdt2 samples. */
> +    int ret, out_size = 0;
>      if (size <= 8)
>          return AVERROR_INVALIDDATA;
> -    new_size = ((size - 8) / 2) * 3;
> -    ret = av_new_packet(pkt, new_size);
> +
> +    /* Allocate 3 times the required buffer size to give us enough space
> +       to store the original c608 packet and (potentially 3/2 times larger)
> +       reformatted data, safely. */
> +    ret = av_new_packet(pkt, size * 3);
>      if (ret < 0)
>          return ret;
>  
> -    avio_skip(pb, 8);
> -    for (int j = 0; j < new_size; j += 3) {
> -        pkt->data[j] = 0xFC;
> -        pkt->data[j+1] = avio_r8(pb);
> -        pkt->data[j+2] = avio_r8(pb);
> +    /* Load the original c608 payload into the last 3rd of the buffer. */
> +    if (avio_read(pb, pkt->data + size * 2, size) != size)
> +        return AVERROR_EOF;
> +
> +    /* parse and re-format the c608 payload in one pass */
> +    for (uint8_t *out = pkt->data, *src = out + size * 2, *end = src + size; src + 8 <= end; ) {
> +        uint32_t atom_size = AV_RB32(src);
> +        uint8_t cc_field =
> +            memcmp(src + 4, "cdat", 4) == 0 ? 1 :
> +            memcmp(src + 4, "cdt2", 4) == 0 ? 2 :
> +            0;
> +
> +        if (cc_field != 0) {
> +            for (uint8_t *cc = src + 8, *cc_end = src + atom_size; cc < cc_end; cc += 2) {
> +                out[0] = (0x1F << 3) | (1 << 2) | (cc_field - 1);
> +                out[1] = cc[0];
> +                out[2] = cc[1];
> +                out_size += 3;
> +                out += 3;
> +            }
> +        }
> +        src += atom_size;
>      }
>  
> +    pkt->size = out_size;
>      return 0;
>  }
>  

1. You are trusting atom_size, although it may be insanely large. This
may lead to segfaults.
2. 3 * size might overflow.
3. You overallocate a lot here. Wouldn't it be enough to allocate size +
size / 2? You would then read into pkt->data + size / 2 and reformat the
data from the start.
4. You need to shrink the packet to zero the padding.
5. You don't need to keep track of out_size; you can get it via out -
pkt->data.

- Andreas