[FFmpeg-devel] [PATCH] avcodec/qpeldsp: copy less for the mc0x cases

[Andreas Rheinhardt]

Michael Niedermayer:
> Fixes: out of array access
> Fixes: 47936/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_MPEG4_fuzzer-5745039940124672
> 
> Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg
> Signed-off-by: Michael Niedermayer <michael at niedermayer.cc>
> ---
>  libavcodec/qpeldsp.c | 12 ++++++------
>  1 file changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/libavcodec/qpeldsp.c b/libavcodec/qpeldsp.c
> index 2b9146ceb1..5f937f9d9e 100644
> --- a/libavcodec/qpeldsp.c
> +++ b/libavcodec/qpeldsp.c
> @@ -199,7 +199,7 @@ static void OPNAME ## qpel8_mc01_c(uint8_t *dst, const uint8_t *src,          \
>      uint8_t full[16 * 9];                                                     \
>      uint8_t half[64];                                                         \
>                                                                                \
> -    copy_block9(full, src, 16, stride, 9);                                    \
> +    copy_block8(full, src, 16, stride, 9);                                    \
>      put ## RND ## mpeg4_qpel8_v_lowpass(half, full, 8, 16);                   \
>      OPNAME ## pixels8_l2_8(dst, full, half, stride, 16, 8, 8);                \
>  }                                                                             \
> @@ -209,7 +209,7 @@ static void OPNAME ## qpel8_mc02_c(uint8_t *dst, const uint8_t *src,          \
>  {                                                                             \
>      uint8_t full[16 * 9];                                                     \
>                                                                                \
> -    copy_block9(full, src, 16, stride, 9);                                    \
> +    copy_block8(full, src, 16, stride, 9);                                    \
>      OPNAME ## mpeg4_qpel8_v_lowpass(dst, full, stride, 16);                   \
>  }                                                                             \
>                                                                                \
> @@ -219,7 +219,7 @@ static void OPNAME ## qpel8_mc03_c(uint8_t *dst, const uint8_t *src,          \
>      uint8_t full[16 * 9];                                                     \
>      uint8_t half[64];                                                         \
>                                                                                \
> -    copy_block9(full, src, 16, stride, 9);                                    \
> +    copy_block8(full, src, 16, stride, 9);                                    \
>      put ## RND ## mpeg4_qpel8_v_lowpass(half, full, 8, 16);                   \
>      OPNAME ## pixels8_l2_8(dst, full + 16, half, stride, 16, 8, 8);           \
>  }                                                                             \
> @@ -459,7 +459,7 @@ static void OPNAME ## qpel16_mc01_c(uint8_t *dst, const uint8_t *src,         \
>      uint8_t full[24 * 17];                                                    \
>      uint8_t half[256];                                                        \
>                                                                                \
> -    copy_block17(full, src, 24, stride, 17);                                  \
> +    copy_block16(full, src, 24, stride, 17);                                  \
>      put ## RND ## mpeg4_qpel16_v_lowpass(half, full, 16, 24);                 \
>      OPNAME ## pixels16_l2_8(dst, full, half, stride, 24, 16, 16);             \
>  }                                                                             \
> @@ -469,7 +469,7 @@ static void OPNAME ## qpel16_mc02_c(uint8_t *dst, const uint8_t *src,         \
>  {                                                                             \
>      uint8_t full[24 * 17];                                                    \
>                                                                                \
> -    copy_block17(full, src, 24, stride, 17);                                  \
> +    copy_block16(full, src, 24, stride, 17);                                  \
>      OPNAME ## mpeg4_qpel16_v_lowpass(dst, full, stride, 24);                  \
>  }                                                                             \
>                                                                                \
> @@ -479,7 +479,7 @@ static void OPNAME ## qpel16_mc03_c(uint8_t *dst, const uint8_t *src,         \
>      uint8_t full[24 * 17];                                                    \
>      uint8_t half[256];                                                        \
>                                                                                \
> -    copy_block17(full, src, 24, stride, 17);                                  \
> +    copy_block16(full, src, 24, stride, 17);                                  \
>      put ## RND ## mpeg4_qpel16_v_lowpass(half, full, 16, 24);                 \
>      OPNAME ## pixels16_l2_8(dst, full + 24, half, stride, 24, 16, 16);        \
>  }                                                                             \

Are the arch-specific dsp functions affected by this, too?
Do you happen to know why copy_block9/17 has been used in this code?
(After all, using copy_block8/16 should result in a slight speedup, so I
using copy_block9/17 must have been intentional.)

- Andreas