Merge remote-tracking branch 'qatar/master'

* qatar/master:
  dv1394: Swap the min and max values of the 'standard' option
  rtpdec_vp8: Don't parse fields that aren't used
  lavc: add some AVPacket doxy.
  audiointerleave: deobfuscate a function call.
  rtpdec: factorize identical code used in several handlers
  a64: remove interleaved mode.
  doc: Point to the new location of the c99-to-c89 tool
  decode_audio3: initialize AVFrame
  ws-snd1: set channel layout
  wmavoice: set channel layout
  wmapro: use AVCodecContext.channels instead of keeping a private copy
  wma: do not keep private copies of some AVCodecContext fields

Conflicts:
	libavcodec/wmadec.c
	libavcodec/wmaenc.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>

18 files changed, 150 insertions, 268 deletions

diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h
index 5344159939..a80612798e 100644
--- a/libavcodec/avcodec.h
+++ b/libavcodec/avcodec.h
@@ -962,6 +962,28 @@ enum AVPacketSideDataType {
     AV_PKT_DATA_SUBTITLE_POSITION,
 };
 
+/**
+ * This structure stores compressed data. It is typically exported by demuxers
+ * and then passed as input to decoders, or received as output from encoders and
+ * then passed to muxers.
+ *
+ * For video, it should typically contain one compressed frame. For audio it may
+ * contain several compressed frames.
+ *
+ * AVPacket is one of the few structs in FFmpeg, whose size is a part of public
+ * ABI. Thus it may be allocated on stack and no new fields can be added to it
+ * without libavcodec and libavformat major bump.
+ *
+ * The semantics of data ownership depends on the destruct field.
+ * If it is set, the packet data is dynamically allocated and is valid
+ * indefinitely until av_free_packet() is called (which in turn calls the
+ * destruct callback to free the data). If destruct is not set, the packet data
+ * is typically backed by some static buffer somewhere and is only valid for a
+ * limited time (e.g. until the next read call when demuxing).
+ *
+ * The side data is always allocated with av_malloc() and is freed in
+ * av_free_packet().
+ */
 typedef struct AVPacket {
     /**
      * Presentation timestamp in AVStream->time_base units; the time at which
diff --git a/libavcodec/utils.c b/libavcodec/utils.c
index 2b7ab46f2a..931f3fd53e 100644
--- a/libavcodec/utils.c
+++ b/libavcodec/utils.c
@@ -1702,7 +1702,7 @@ int attribute_align_arg avcodec_decode_audio3(AVCodecContext *avctx, int16_t *sa
                                               int *frame_size_ptr,
                                               AVPacket *avpkt)
 {
-    AVFrame frame;
+    AVFrame frame = {0};
     int ret, got_frame = 0;
 
     if (avctx->get_buffer != avcodec_default_get_buffer) {
diff --git a/libavcodec/wma.c b/libavcodec/wma.c
index c65281711a..d0c0b34868 100644
--- a/libavcodec/wma.c
+++ b/libavcodec/wma.c
@@ -82,11 +82,6 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
         || avctx->bit_rate    <= 0)
         return -1;
 
-    s->sample_rate = avctx->sample_rate;
-    s->nb_channels = avctx->channels;
-    s->bit_rate    = avctx->bit_rate;
-    s->block_align = avctx->block_align;
-
     ff_dsputil_init(&s->dsp, avctx);
     ff_fmt_convert_init(&s->fmt_conv, avctx);
     avpriv_float_dsp_init(&s->fdsp, avctx->flags & CODEC_FLAG_BITEXACT);
@@ -98,7 +93,8 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
     }
 
     /* compute MDCT block size */
-    s->frame_len_bits = ff_wma_get_frame_len_bits(s->sample_rate, s->version, 0);
+    s->frame_len_bits = ff_wma_get_frame_len_bits(avctx->sample_rate,
+                                                  s->version, 0);
     s->next_block_len_bits = s->frame_len_bits;
     s->prev_block_len_bits = s->frame_len_bits;
     s->block_len_bits      = s->frame_len_bits;
@@ -107,7 +103,7 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
     if (s->use_variable_block_len) {
         int nb_max, nb;
         nb = ((flags2 >> 3) & 3) + 1;
-        if ((s->bit_rate / s->nb_channels) >= 32000)
+        if ((avctx->bit_rate / avctx->channels) >= 32000)
             nb += 2;
         nb_max = s->frame_len_bits - BLOCK_MIN_BITS;
         if (nb > nb_max)
@@ -119,10 +115,10 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
 
     /* init rate dependent parameters */
     s->use_noise_coding = 1;
-    high_freq = s->sample_rate * 0.5;
+    high_freq = avctx->sample_rate * 0.5;
 
     /* if version 2, then the rates are normalized */
-    sample_rate1 = s->sample_rate;
+    sample_rate1 = avctx->sample_rate;
     if (s->version == 2) {
         if (sample_rate1 >= 44100) {
             sample_rate1 = 44100;
@@ -137,13 +133,13 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
         }
     }
 
-    bps = (float)s->bit_rate / (float)(s->nb_channels * s->sample_rate);
+    bps = (float)avctx->bit_rate / (float)(avctx->channels * avctx->sample_rate);
     s->byte_offset_bits = av_log2((int)(bps * s->frame_len / 8.0 + 0.5)) + 2;
 
     /* compute high frequency value and choose if noise coding should
        be activated */
     bps1 = bps;
-    if (s->nb_channels == 2)
+    if (avctx->channels == 2)
         bps1 = bps * 1.6;
     if (sample_rate1 == 44100) {
         if (bps1 >= 0.61) {
@@ -186,8 +182,8 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
     }
     av_dlog(s->avctx, "flags2=0x%x\n", flags2);
     av_dlog(s->avctx, "version=%d channels=%d sample_rate=%d bitrate=%d block_align=%d\n",
-            s->version, s->nb_channels, s->sample_rate, s->bit_rate,
-            s->block_align);
+            s->version, avctx->channels, avctx->sample_rate, avctx->bit_rate,
+            avctx->block_align);
     av_dlog(s->avctx, "bps=%f bps1=%f high_freq=%f bitoffset=%d\n",
             bps, bps1, high_freq, s->byte_offset_bits);
     av_dlog(s->avctx, "use_noise_coding=%d use_exp_vlc=%d nb_block_sizes=%d\n",
@@ -210,7 +206,7 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
                 lpos = 0;
                 for (i = 0; i < 25; i++) {
                     a = ff_wma_critical_freqs[i];
-                    b = s->sample_rate;
+                    b = avctx->sample_rate;
                     pos = ((block_len * 2 * a) + (b >> 1)) / b;
                     if (pos > block_len)
                         pos = block_len;
@@ -227,11 +223,11 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
                 table = NULL;
                 a = s->frame_len_bits - BLOCK_MIN_BITS - k;
                 if (a < 3) {
-                    if (s->sample_rate >= 44100) {
+                    if (avctx->sample_rate >= 44100) {
                         table = exponent_band_44100[a];
-                    } else if (s->sample_rate >= 32000) {
+                    } else if (avctx->sample_rate >= 32000) {
                         table = exponent_band_32000[a];
-                    } else if (s->sample_rate >= 22050) {
+                    } else if (avctx->sample_rate >= 22050) {
                         table = exponent_band_22050[a];
                     }
                 }
@@ -245,7 +241,7 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
                     lpos = 0;
                     for (i = 0; i < 25; i++) {
                         a = ff_wma_critical_freqs[i];
-                        b = s->sample_rate;
+                        b = avctx->sample_rate;
                         pos = ((block_len * 2 * a) + (b << 1)) / (4 * b);
                         pos <<= 2;
                         if (pos > block_len)
@@ -264,7 +260,7 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
             s->coefs_end[k] = (s->frame_len - ((s->frame_len * 9) / 100)) >> k;
             /* high freq computation */
             s->high_band_start[k] = (int)((block_len * 2 * high_freq) /
-                                          s->sample_rate + 0.5);
+                                          avctx->sample_rate + 0.5);
             n = s->exponent_sizes[k];
             j = 0;
             pos = 0;
@@ -344,7 +340,7 @@ int ff_wma_init(AVCodecContext *avctx, int flags2)
 
     /* choose the VLC tables for the coefficients */
     coef_vlc_table = 2;
-    if (s->sample_rate >= 32000) {
+    if (avctx->sample_rate >= 32000) {
         if (bps1 < 0.72) {
             coef_vlc_table = 0;
         } else if (bps1 < 1.16) {
diff --git a/libavcodec/wma.h b/libavcodec/wma.h
index 1e7f0e5aba..4db4faa54a 100644
--- a/libavcodec/wma.h
+++ b/libavcodec/wma.h
@@ -69,11 +69,7 @@ typedef struct WMACodecContext {
     AVFrame frame;
     GetBitContext gb;
     PutBitContext pb;
-    int sample_rate;
-    int nb_channels;
-    int bit_rate;
     int version;                            ///< 1 = 0x160 (WMAV1), 2 = 0x161 (WMAV2)
-    int block_align;
     int use_bit_reservoir;
     int use_variable_block_len;
     int use_exp_vlc;                        ///< exponent coding: 0 = lsp, 1 = vlc + delta
diff --git a/libavcodec/wmadec.c b/libavcodec/wmadec.c
index ca12d24031..f3ce474f41 100644
--- a/libavcodec/wmadec.c
+++ b/libavcodec/wmadec.c
@@ -487,11 +487,11 @@ static int wma_decode_block(WMACodecContext *s)
         return -1;
     }
 
-    if (s->nb_channels == 2) {
+    if (s->avctx->channels == 2) {
         s->ms_stereo = get_bits1(&s->gb);
     }
     v = 0;
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for(ch = 0; ch < s->avctx->channels; ch++) {
         a = get_bits1(&s->gb);
         s->channel_coded[ch] = a;
         v |= a;
@@ -518,13 +518,13 @@ static int wma_decode_block(WMACodecContext *s)
 
     /* compute number of coefficients */
     n = s->coefs_end[bsize] - s->coefs_start;
-    for(ch = 0; ch < s->nb_channels; ch++)
+    for(ch = 0; ch < s->avctx->channels; ch++)
         nb_coefs[ch] = n;
 
     /* complex coding */
     if (s->use_noise_coding) {
 
-        for(ch = 0; ch < s->nb_channels; ch++) {
+        for(ch = 0; ch < s->avctx->channels; ch++) {
             if (s->channel_coded[ch]) {
                 int i, n, a;
                 n = s->exponent_high_sizes[bsize];
@@ -537,7 +537,7 @@ static int wma_decode_block(WMACodecContext *s)
                 }
             }
         }
-        for(ch = 0; ch < s->nb_channels; ch++) {
+        for(ch = 0; ch < s->avctx->channels; ch++) {
             if (s->channel_coded[ch]) {
                 int i, n, val, code;
 
@@ -565,7 +565,7 @@ static int wma_decode_block(WMACodecContext *s)
     /* exponents can be reused in short blocks. */
     if ((s->block_len_bits == s->frame_len_bits) ||
         get_bits1(&s->gb)) {
-        for(ch = 0; ch < s->nb_channels; ch++) {
+        for(ch = 0; ch < s->avctx->channels; ch++) {
             if (s->channel_coded[ch]) {
                 if (s->use_exp_vlc) {
                     if (decode_exp_vlc(s, ch) < 0)
@@ -579,7 +579,7 @@ static int wma_decode_block(WMACodecContext *s)
     }
 
     /* parse spectral coefficients : just RLE encoding */
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         if (s->channel_coded[ch]) {
             int tindex;
             WMACoef* ptr = &s->coefs1[ch][0];
@@ -593,7 +593,7 @@ static int wma_decode_block(WMACodecContext *s)
                   0, ptr, 0, nb_coefs[ch],
                   s->block_len, s->frame_len_bits, coef_nb_bits);
         }
-        if (s->version == 1 && s->nb_channels >= 2) {
+        if (s->version == 1 && s->avctx->channels >= 2) {
             align_get_bits(&s->gb);
         }
     }
@@ -608,7 +608,7 @@ static int wma_decode_block(WMACodecContext *s)
     }
 
     /* finally compute the MDCT coefficients */
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         if (s->channel_coded[ch]) {
             WMACoef *coefs1;
             float *coefs, *exponents, mult, mult1, noise;
@@ -712,7 +712,7 @@ static int wma_decode_block(WMACodecContext *s)
     }
 
 #ifdef TRACE
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         if (s->channel_coded[ch]) {
             dump_floats(s, "exponents", 3, s->exponents[ch], s->block_len);
             dump_floats(s, "coefs", 1, s->coefs[ch], s->block_len);
@@ -736,7 +736,7 @@ static int wma_decode_block(WMACodecContext *s)
 next:
     mdct = &s->mdct_ctx[bsize];
 
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         int n4, index;
 
         n4 = s->block_len / 2;
@@ -780,7 +780,7 @@ static int wma_decode_frame(WMACodecContext *s, float **samples,
             break;
     }
 
-    for (ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         /* copy current block to output */
         memcpy(samples[ch] + samples_offset, s->frame_out[ch],
                s->frame_len * sizeof(*s->frame_out[ch]));
@@ -813,14 +813,14 @@ static int wma_decode_superframe(AVCodecContext *avctx, void *data,
         s->last_superframe_len = 0;
         return 0;
     }
-    if (buf_size < s->block_align) {
+    if (buf_size < avctx->block_align) {
         av_log(avctx, AV_LOG_ERROR,
                "Input packet size too small (%d < %d)\n",
-               buf_size, s->block_align);
+               buf_size, avctx->block_align);
         return AVERROR_INVALIDDATA;
     }
-    if(s->block_align)
-        buf_size = s->block_align;
+    if(avctx->block_align)
+        buf_size = avctx->block_align;
 
     init_get_bits(&s->gb, buf, buf_size*8);
 
@@ -915,7 +915,7 @@ static int wma_decode_superframe(AVCodecContext *avctx, void *data,
 
     av_dlog(s->avctx, "%d %d %d %d outbytes:%td eaten:%d\n",
             s->frame_len_bits, s->block_len_bits, s->frame_len, s->block_len,
-            (int8_t *)samples - (int8_t *)data, s->block_align);
+            (int8_t *)samples - (int8_t *)data, avctx->block_align);
 
     *got_frame_ptr   = 1;
     *(AVFrame *)data = s->frame;
diff --git a/libavcodec/wmaenc.c b/libavcodec/wmaenc.c
index 63f815c78a..bf5c2b1254 100644
--- a/libavcodec/wmaenc.c
+++ b/libavcodec/wmaenc.c
@@ -27,7 +27,7 @@
 
 static int encode_init(AVCodecContext * avctx){
     WMACodecContext *s = avctx->priv_data;
-    int i, flags1, flags2;
+    int i, flags1, flags2, block_align;
     uint8_t *extradata;
 
     s->avctx = avctx;
@@ -78,10 +78,11 @@ static int encode_init(AVCodecContext * avctx){
     for(i = 0; i < s->nb_block_sizes; i++)
         ff_mdct_init(&s->mdct_ctx[i], s->frame_len_bits - i + 1, 0, 1.0);
 
-    s->block_align     = avctx->bit_rate * (int64_t)s->frame_len /
+    block_align        = avctx->bit_rate * (int64_t)s->frame_len /
                          (avctx->sample_rate * 8);
-    s->block_align     = FFMIN(s->block_align, MAX_CODED_SUPERFRAME_SIZE);
-    avctx->block_align = s->block_align;
+    block_align        = FFMIN(block_align, MAX_CODED_SUPERFRAME_SIZE);
+    avctx->block_align = block_align;
+
     avctx->frame_size = avctx->delay = s->frame_len;
 
 #if FF_API_OLD_ENCODE_AUDIO
@@ -184,7 +185,7 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
 
     //FIXME factor
     v = s->coefs_end[bsize] - s->coefs_start;
-    for(ch = 0; ch < s->nb_channels; ch++)
+    for (ch = 0; ch < s->avctx->channels; ch++)
         nb_coefs[ch] = v;
     {
         int n4 = s->block_len / 2;
@@ -194,18 +195,18 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
         }
     }
 
-    if (s->nb_channels == 2) {
+    if (s->avctx->channels == 2) {
         put_bits(&s->pb, 1, !!s->ms_stereo);
     }
 
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         s->channel_coded[ch] = 1; //FIXME only set channel_coded when needed, instead of always
         if (s->channel_coded[ch]) {
             init_exp(s, ch, fixed_exp);
         }
     }
 
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         if (s->channel_coded[ch]) {
             WMACoef *coefs1;
             float *coefs, *exponents, mult;
@@ -233,7 +234,7 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
     }
 
     v = 0;
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         int a = s->channel_coded[ch];
         put_bits(&s->pb, 1, a);
         v |= a;
@@ -249,7 +250,7 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
     coef_nb_bits= ff_wma_total_gain_to_bits(total_gain);
 
     if (s->use_noise_coding) {
-        for(ch = 0; ch < s->nb_channels; ch++) {
+        for (ch = 0; ch < s->avctx->channels; ch++) {
             if (s->channel_coded[ch]) {
                 int i, n;
                 n = s->exponent_high_sizes[bsize];
@@ -268,7 +269,7 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
     }
 
     if (parse_exponents) {
-        for(ch = 0; ch < s->nb_channels; ch++) {
+        for (ch = 0; ch < s->avctx->channels; ch++) {
             if (s->channel_coded[ch]) {
                 if (s->use_exp_vlc) {
                     encode_exp_vlc(s, ch, fixed_exp);
@@ -282,7 +283,7 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
         av_assert0(0); //FIXME not implemented
     }
 
-    for(ch = 0; ch < s->nb_channels; ch++) {
+    for (ch = 0; ch < s->avctx->channels; ch++) {
         if (s->channel_coded[ch]) {
             int run, tindex;
             WMACoef *ptr, *eptr;
@@ -320,7 +321,7 @@ static int encode_block(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
             if(run)
                 put_bits(&s->pb, s->coef_vlcs[tindex]->huffbits[1], s->coef_vlcs[tindex]->huffcodes[1]);
         }
-        if (s->version == 1 && s->nb_channels >= 2) {
+        if (s->version == 1 && s->avctx->channels >= 2) {
             avpriv_align_put_bits(&s->pb);
         }
     }
@@ -339,7 +340,7 @@ static int encode_frame(WMACodecContext *s, float (*src_coefs)[BLOCK_MAX_SIZE],
 
     avpriv_align_put_bits(&s->pb);
 
-    return put_bits_count(&s->pb)/8 - s->block_align;
+    return put_bits_count(&s->pb) / 8 - s->avctx->block_align;
 }
 
 static int encode_superframe(AVCodecContext *avctx, AVPacket *avpkt,
@@ -379,18 +380,18 @@ static int encode_superframe(AVCodecContext *avctx, AVPacket *avpkt,
     while(total_gain <= 128 && error > 0)
         error = encode_frame(s, s->coefs, avpkt->data, avpkt->size, total_gain++);
     av_assert0((put_bits_count(&s->pb) & 7) == 0);
-    i= s->block_align - (put_bits_count(&s->pb)+7)/8;
+    i= avctx->block_align - (put_bits_count(&s->pb)+7)/8;
     av_assert0(i>=0);
     while(i--)
         put_bits(&s->pb, 8, 'N');
 
     flush_put_bits(&s->pb);
-    av_assert0(put_bits_ptr(&s->pb) - s->pb.buf == s->block_align);
+    av_assert0(put_bits_ptr(&s->pb) - s->pb.buf == avctx->block_align);
 
     if (frame->pts != AV_NOPTS_VALUE)
         avpkt->pts = frame->pts - ff_samples_to_time_base(avctx, avctx->delay);
 
-    avpkt->size = s->block_align;
+    avpkt->size = avctx->block_align;
     *got_packet_ptr = 1;
     return 0;
 }
diff --git a/libavcodec/wmaprodec.c b/libavcodec/wmaprodec.c
index 4d15e45875..e071eb1f95 100644
--- a/libavcodec/wmaprodec.c
+++ b/libavcodec/wmaprodec.c
@@ -184,7 +184,6 @@ typedef struct WMAProDecodeCtx {
     uint8_t          bits_per_sample;               ///< integer audio sample size for the unscaled IMDCT output (used to scale to [-1.0, 1.0])
     uint16_t         samples_per_frame;             ///< number of samples to output
     uint16_t         log2_frame_size;
-    int8_t           num_channels;                  ///< number of channels in the stream (same as AVCodecContext.num_channels)
     int8_t           lfe_channel;                   ///< lfe channel index
     uint8_t          max_num_subframes;
     uint8_t          subframe_len_bits;             ///< number of bits used for the subframe length
@@ -246,7 +245,7 @@ static av_cold void dump_context(WMAProDecodeCtx *s)
     PRINT("log2 frame size",     s->log2_frame_size);
     PRINT("max num subframes",   s->max_num_subframes);
     PRINT("len prefix",          s->len_prefix);
-    PRINT("num channels",        s->num_channels);
+    PRINT("num channels",        s->avctx->channels);
 }
 
 /**
@@ -343,18 +342,17 @@ static av_cold int decode_init(AVCodecContext *avctx)
         return AVERROR_INVALIDDATA;
     }
 
-    s->num_channels = avctx->channels;
-
-    if (s->num_channels < 0) {
-        av_log(avctx, AV_LOG_ERROR, "invalid number of channels %d\n", s->num_channels);
+    if (avctx->channels < 0) {
+        av_log(avctx, AV_LOG_ERROR, "invalid number of channels %d\n",
+               avctx->channels);
         return AVERROR_INVALIDDATA;
-    } else if (s->num_channels > WMAPRO_MAX_CHANNELS) {
+    } else if (avctx->channels > WMAPRO_MAX_CHANNELS) {
         av_log_ask_for_sample(avctx, "unsupported number of channels\n");
         return AVERROR_PATCHWELCOME;
     }
 
     /** init previous block len */
-    for (i = 0; i < s->num_channels; i++)
+    for (i = 0; i < avctx->channels; i++)
         s->channel[i].prev_block_len = s->samples_per_frame;
 
     /** extract lfe channel position */
@@ -531,7 +529,7 @@ static int decode_tilehdr(WMAProDecodeCtx *s)
 {
     uint16_t num_samples[WMAPRO_MAX_CHANNELS] = { 0 };/**< sum of samples for all currently known subframes of a channel */
     uint8_t  contains_subframe[WMAPRO_MAX_CHANNELS];  /**< flag indicating if a channel contains the current subframe */
-    int channels_for_cur_subframe = s->num_channels;  /**< number of channels that contain the current subframe */
+    int channels_for_cur_subframe = s->avctx->channels; /**< number of channels that contain the current subframe */
     int fixed_channel_layout = 0;                     /**< flag indicating that all channels use the same subframe offsets and sizes */
     int min_channel_len = 0;                          /**< smallest sum of samples (channels with this length will be processed first) */
     int c;
@@ -543,7 +541,7 @@ static int decode_tilehdr(WMAProDecodeCtx *s)
      */
 
     /** reset tiling information */
-    for (c = 0; c < s->num_channels; c++)
+    for (c = 0; c < s->avctx->channels; c++)
         s->channel[c].num_subframes = 0;
 
     if (s->max_num_subframes == 1 || get_bits1(&s->gb))
@@ -554,7 +552,7 @@ static int decode_tilehdr(WMAProDecodeCtx *s)
         int subframe_len;
 
         /** check which channels contain the subframe */
-        for (c = 0; c < s->num_channels; c++) {
+        for (c = 0; c < s->avctx->channels; c++) {
             if (num_samples[c] == min_channel_len) {
                 if (fixed_channel_layout || channels_for_cur_subframe == 1 ||
                    (min_channel_len == s->samples_per_frame - s->min_samples_per_subframe))
@@ -571,7 +569,7 @@ static int decode_tilehdr(WMAProDecodeCtx *s)
 
         /** add subframes to the individual channels and find new min_channel_len */
         min_channel_len += subframe_len;
-        for (c = 0; c < s->num_channels; c++) {
+        for (c = 0; c < s->avctx->channels; c++) {
             WMAProChannelCtx* chan = &s->channel[c];
 
             if (contains_subframe[c]) {
@@ -598,7 +596,7 @@ static int decode_tilehdr(WMAProDecodeCtx *s)
         }
     } while (min_channel_len < s->samples_per_frame);
 
-    for (c = 0; c < s->num_channels; c++) {
+    for (c = 0; c < s->avctx->channels; c++) {
         int i;
         int offset = 0;
         for (i = 0; i < s->channel[c].num_subframes; i++) {
@@ -624,8 +622,8 @@ static void decode_decorrelation_matrix(WMAProDecodeCtx *s,
     int i;
     int offset = 0;
     int8_t rotation_offset[WMAPRO_MAX_CHANNELS * WMAPRO_MAX_CHANNELS];
-    memset(chgroup->decorrelation_matrix, 0, s->num_channels *
-           s->num_channels * sizeof(*chgroup->decorrelation_matrix));
+    memset(chgroup->decorrelation_matrix, 0, s->avctx->channels *
+           s->avctx->channels * sizeof(*chgroup->decorrelation_matrix));
 
     for (i = 0; i < chgroup->num_channels * (chgroup->num_channels - 1) >> 1; i++)
         rotation_offset[i] = get_bits(&s->gb, 6);
@@ -678,7 +676,7 @@ static int decode_channel_transform(WMAProDecodeCtx* s)
 
     /** in the one channel case channel transforms are pointless */
     s->num_chgroups = 0;
-    if (s->num_channels > 1) {
+    if (s->avctx->channels > 1) {
         int remaining_channels = s->channels_for_cur_subframe;
 
         if (get_bits1(&s->gb)) {
@@ -724,7 +722,7 @@ static int decode_channel_transform(WMAProDecodeCtx* s)
                     }
                 } else {
                     chgroup->transform = 1;
-                    if (s->num_channels == 2) {
+                    if (s->avctx->channels == 2) {
                         chgroup->decorrelation_matrix[0] =  1.0;
                         chgroup->decorrelation_matrix[1] = -1.0;
                         chgroup->decorrelation_matrix[2] =  1.0;
@@ -1014,7 +1012,7 @@ static void inverse_channel_transform(WMAProDecodeCtx *s)
                             (*ch)[y] = sum;
                         }
                     }
-                } else if (s->num_channels == 2) {
+                } else if (s->avctx->channels == 2) {
                     int len = FFMIN(sfb[1], s->subframe_len) - sfb[0];
                     s->dsp.vector_fmul_scalar(ch_data[0] + sfb[0],
                                               ch_data[0] + sfb[0],
@@ -1067,7 +1065,7 @@ static int decode_subframe(WMAProDecodeCtx *s)
     int offset = s->samples_per_frame;
     int subframe_len = s->samples_per_frame;
     int i;
-    int total_samples   = s->samples_per_frame * s->num_channels;
+    int total_samples   = s->samples_per_frame * s->avctx->channels;
     int transmit_coeffs = 0;
     int cur_subwoofer_cutoff;
 
@@ -1077,7 +1075,7 @@ static int decode_subframe(WMAProDecodeCtx *s)
         == the next block of the channel with the smallest number of
         decoded samples
     */
-    for (i = 0; i < s->num_channels; i++) {
+    for (i = 0; i < s->avctx->channels; i++) {
         s->channel[i].grouped = 0;
         if (offset > s->channel[i].decoded_samples) {
             offset = s->channel[i].decoded_samples;
@@ -1091,7 +1089,7 @@ static int decode_subframe(WMAProDecodeCtx *s)
 
     /** get a list of all channels that contain the estimated block */
     s->channels_for_cur_subframe = 0;
-    for (i = 0; i < s->num_channels; i++) {
+    for (i = 0; i < s->avctx->channels; i++) {
         const int cur_subframe = s->channel[i].cur_subframe;
         /** substract already processed samples */
         total_samples -= s->channel[i].decoded_samples;
@@ -1321,9 +1319,9 @@ static int decode_frame(WMAProDecodeCtx *s, int *got_frame_ptr)
     }
 
     /** read postproc transform */
-    if (s->num_channels > 1 && get_bits1(gb)) {
+    if (s->avctx->channels > 1 && get_bits1(gb)) {
         if (get_bits1(gb)) {
-            for (i = 0; i < s->num_channels * s->num_channels; i++)
+            for (i = 0; i < avctx->channels * avctx->channels; i++)
                 skip_bits(gb, 4);
         }
     }
@@ -1358,7 +1356,7 @@ static int decode_frame(WMAProDecodeCtx *s, int *got_frame_ptr)
 
     /** reset subframe states */
     s->parsed_all_subframes = 0;
-    for (i = 0; i < s->num_channels; i++) {
+    for (i = 0; i < avctx->channels; i++) {
         s->channel[i].decoded_samples = 0;
         s->channel[i].cur_subframe    = 0;
         s->channel[i].reuse_sf        = 0;
@@ -1381,11 +1379,11 @@ static int decode_frame(WMAProDecodeCtx *s, int *got_frame_ptr)
     }
 
     /** copy samples to the output buffer */
-    for (i = 0; i < s->num_channels; i++)
+    for (i = 0; i < avctx->channels; i++)
         memcpy(s->frame.extended_data[i], s->channel[i].out,
                s->samples_per_frame * sizeof(*s->channel[i].out));
 
-    for (i = 0; i < s->num_channels; i++) {
+    for (i = 0; i < avctx->channels; i++) {
         /** reuse second half of the IMDCT output for the next frame */
         memcpy(&s->channel[i].out[0],
                &s->channel[i].out[s->samples_per_frame],
@@ -1615,7 +1613,7 @@ static void flush(AVCodecContext *avctx)
     int i;
     /** reset output buffer as a part of it is used during the windowing of a
         new frame */
-    for (i = 0; i < s->num_channels; i++)
+    for (i = 0; i < avctx->channels; i++)
         memset(s->channel[i].out, 0, s->samples_per_frame *
                sizeof(*s->channel[i].out));
     s->packet_loss = 1;
diff --git a/libavcodec/wmavoice.c b/libavcodec/wmavoice.c
index 9504dab3f1..f4e156e92e 100644
--- a/libavcodec/wmavoice.c
+++ b/libavcodec/wmavoice.c
@@ -29,6 +29,7 @@
 
 #include <math.h>
 
+#include "libavutil/audioconvert.h"
 #include "libavutil/mem.h"
 #include "dsputil.h"
 #include "avcodec.h"
@@ -439,6 +440,8 @@ static av_cold int wmavoice_decode_init(AVCodecContext *ctx)
                                   2 * (s->block_conv_table[1] - 2 * s->min_pitch_val);
     s->block_pitch_nbits        = av_ceil_log2(s->block_pitch_range);
 
+    ctx->channels               = 1;
+    ctx->channel_layout         = AV_CH_LAYOUT_MONO;
     ctx->sample_fmt             = AV_SAMPLE_FMT_FLT;
 
     avcodec_get_frame_defaults(&s->frame);
diff --git a/libavcodec/ws-snd1.c b/libavcodec/ws-snd1.c
index dfa02b6954..3a83f94e41 100644
--- a/libavcodec/ws-snd1.c
+++ b/libavcodec/ws-snd1.c
@@ -20,6 +20,8 @@
  */
 
 #include <stdint.h>
+
+#include "libavutil/audioconvert.h"
 #include "libavutil/common.h"
 #include "libavutil/intreadwrite.h"
 #include "avcodec.h"
@@ -46,12 +48,9 @@ static av_cold int ws_snd_decode_init(AVCodecContext *avctx)
 {
     WSSndContext *s = avctx->priv_data;
 
-    if (avctx->channels != 1) {
-        av_log_ask_for_sample(avctx, "unsupported number of channels\n");
-        return AVERROR(EINVAL);
-    }
-
-    avctx->sample_fmt = AV_SAMPLE_FMT_U8;
+    avctx->channels       = 1;
+    avctx->channel_layout = AV_CH_LAYOUT_MONO;
+    avctx->sample_fmt     = AV_SAMPLE_FMT_U8;
 
     avcodec_get_frame_defaults(&s->frame);
     avctx->coded_frame = &s->frame;
diff --git a/libavformat/a64.c b/libavformat/a64.c
index c1f6b67904..c672fb698c 100644
--- a/libavformat/a64.c
+++ b/libavformat/a64.c
@@ -23,17 +23,11 @@
 #include "libavcodec/a64enc.h"
 #include "libavcodec/bytestream.h"
 #include "avformat.h"
-
-typedef struct A64MuxerContext {
-    int interleaved;
-    AVPacket prev_pkt;
-    int prev_frame_count;
-} A64MuxerContext;
+#include "rawenc.h"
 
 static int a64_write_header(struct AVFormatContext *s)
 {
     AVCodecContext *avctx = s->streams[0]->codec;
-    A64MuxerContext *c = s->priv_data;
     uint8_t header[5] = {
         0x00, //load
         0x40, //address
@@ -41,7 +35,6 @@ static int a64_write_header(struct AVFormatContext *s)
         0x00, //charset_lifetime (multi only)
         0x00  //fps in 50/fps;
     };
-    c->interleaved = 0;
     switch (avctx->codec->id) {
     case AV_CODEC_ID_A64_MULTI:
         header[2] = 0x00;
@@ -57,109 +50,6 @@ static int a64_write_header(struct AVFormatContext *s)
         return AVERROR(EINVAL);
     }
     avio_write(s->pb, header, 2);
-    c->prev_pkt.size = 0;
-    c->prev_frame_count = 0;
-    return 0;
-}
-
-static int a64_write_packet(struct AVFormatContext *s, AVPacket *pkt)
-{
-    AVCodecContext *avctx = s->streams[0]->codec;
-    A64MuxerContext *c = s->priv_data;
-    int i, j;
-    int ch_chunksize;
-    int lifetime;
-    int frame_count;
-    int charset_size;
-    int frame_size;
-    int num_frames;
-
-    /* fetch values from extradata */
-    switch (avctx->codec->id) {
-    case AV_CODEC_ID_A64_MULTI:
-    case AV_CODEC_ID_A64_MULTI5:
-        if(c->interleaved) {
-            /* Write interleaved, means we insert chunks of the future charset before each current frame.
-             * Reason: if we load 1 charset + corresponding frames in one block on c64, we need to store
-             * them first and then display frame by frame to keep in sync. Thus we would read and write
-             * the data for colram from/to ram first and waste too much time. If we interleave and send the
-             * charset beforehand, we assemble a new charset chunk by chunk, write current screen data to
-             * screen-ram to be displayed and decode the colram directly to colram-location $d800 during
-             * the overscan, while reading directly from source.
-             * This is the only way so far, to achieve 25fps on c64 */
-            if(avctx->extradata) {
-                /* fetch values from extradata */
-                lifetime     = AV_RB32(avctx->extradata + 0);
-                frame_count  = AV_RB32(avctx->extradata + 4);
-                charset_size = AV_RB32(avctx->extradata + 8);
-                frame_size   = AV_RB32(avctx->extradata + 12);
-
-                /* TODO: sanity checks? */
-            } else {
-                av_log(avctx, AV_LOG_ERROR, "extradata not set\n");
-                return AVERROR(EINVAL);
-            }
-
-            ch_chunksize=charset_size/lifetime;
-            /* TODO: check if charset/size is % lifetime, but maybe check in codec */
-
-            if(pkt->data) num_frames = lifetime;
-            else num_frames = c->prev_frame_count;
-
-            for(i = 0; i < num_frames; i++) {
-                if(pkt->data) {
-                    /* if available, put newest charset chunk into buffer */
-                    avio_write(s->pb, pkt->data + ch_chunksize * i, ch_chunksize);
-                } else {
-                    /* a bit ugly, but is there an alternative to put many zeros? */
-                    for(j = 0; j < ch_chunksize; j++) avio_w8(s->pb, 0);
-                }
-
-                if(c->prev_pkt.data) {
-                    /* put frame (screen + colram) from last packet into buffer */
-                    avio_write(s->pb, c->prev_pkt.data + charset_size + frame_size * i, frame_size);
-                } else {
-                    /* a bit ugly, but is there an alternative to put many zeros? */
-                    for(j = 0; j < frame_size; j++) avio_w8(s->pb, 0);
-                }
-            }
-
-            /* backup current packet for next turn */
-            if(pkt->data) {
-                /* no backup packet yet? create one! */
-                if(!c->prev_pkt.data) av_new_packet(&c->prev_pkt, pkt->size);
-                /* we have a packet and data is big enough, reuse it */
-                if(c->prev_pkt.data && c->prev_pkt.size >= pkt->size) {
-                    memcpy(c->prev_pkt.data, pkt->data, pkt->size);
-                    c->prev_pkt.size = pkt->size;
-                } else {
-                    av_log(avctx, AV_LOG_ERROR, "Too less memory for prev_pkt.\n");
-                    return AVERROR(ENOMEM);
-                }
-            }
-
-            c->prev_frame_count = frame_count;
-            break;
-        }
-        default:
-            /* Write things as is. Nice for self-contained frames from non-multicolor modes or if played
-             * directly from ram and not from a streaming device (rrnet/mmc) */
-            if(pkt) avio_write(s->pb, pkt->data, pkt->size);
-        break;
-    }
-
-    avio_flush(s->pb);
-    return 0;
-}
-
-static int a64_write_trailer(struct AVFormatContext *s)
-{
-    A64MuxerContext *c = s->priv_data;
-    AVPacket pkt = {0};
-    /* need to flush last packet? */
-    if(c->interleaved) a64_write_packet(s, &pkt);
-    /* discard backed up packet */
-    if(c->prev_pkt.data) av_destruct_packet(&c->prev_pkt);
     return 0;
 }
 
@@ -167,9 +57,7 @@ AVOutputFormat ff_a64_muxer = {
     .name           = "a64",
     .long_name      = NULL_IF_CONFIG_SMALL("a64 - video for Commodore 64"),
     .extensions     = "a64, A64",
-    .priv_data_size = sizeof (A64Context),
     .video_codec    = AV_CODEC_ID_A64_MULTI,
     .write_header   = a64_write_header,
-    .write_packet   = a64_write_packet,
-    .write_trailer  = a64_write_trailer,
+    .write_packet   = ff_raw_write_packet,
 };
diff --git a/libavformat/audiointerleave.c b/libavformat/audiointerleave.c
index 20323a2c58..35dd8d5e62 100644
--- a/libavformat/audiointerleave.c
+++ b/libavformat/audiointerleave.c
@@ -144,5 +144,5 @@ int ff_audio_rechunk_interleave(AVFormatContext *s, AVPacket *out, AVPacket *pkt
         }
     }
 
-    return get_packet(s, out, pkt, flush);
+    return get_packet(s, out, NULL, flush);
 }
diff --git a/libavformat/rtpdec.c b/libavformat/rtpdec.c
index 18cc16fcfe..e92419d9d9 100644
--- a/libavformat/rtpdec.c
+++ b/libavformat/rtpdec.c
@@ -806,3 +806,14 @@ int ff_parse_fmtp(AVStream *stream, PayloadContext *data, const char *p,
     av_free(value);
     return 0;
 }
+
+int ff_rtp_finalize_packet(AVPacket *pkt, AVIOContext **dyn_buf, int stream_idx)
+{
+    av_init_packet(pkt);
+
+    pkt->size = avio_close_dyn_buf(*dyn_buf, &pkt->data);
+    pkt->stream_index = stream_idx;
+    pkt->destruct     = av_destruct_packet;
+    *dyn_buf = NULL;
+    return pkt->size;
+}
diff --git a/libavformat/rtpdec.h b/libavformat/rtpdec.h
index 3d7019024a..15d472a972 100644
--- a/libavformat/rtpdec.h
+++ b/libavformat/rtpdec.h
@@ -202,4 +202,9 @@ int ff_parse_fmtp(AVStream *stream, PayloadContext *data, const char *p,
 
 void av_register_rtp_dynamic_payload_handlers(void);
 
+/**
+ * Close the dynamic buffer and make a packet from it.
+ */
+int ff_rtp_finalize_packet(AVPacket *pkt, AVIOContext **dyn_buf, int stream_idx);
+
 #endif /* AVFORMAT_RTPDEC_H */
diff --git a/libavformat/rtpdec_h263_rfc2190.c b/libavformat/rtpdec_h263_rfc2190.c
index 163d4eaba7..4957b337c7 100644
--- a/libavformat/rtpdec_h263_rfc2190.c
+++ b/libavformat/rtpdec_h263_rfc2190.c
@@ -61,7 +61,7 @@ static int h263_handle_packet(AVFormatContext *ctx, PayloadContext *data,
 {
     /* Corresponding to header fields in the RFC */
     int f, p, i, sbit, ebit, src, r;
-    int header_size;
+    int header_size, ret;
 
     if (data->newformat)
         return ff_h263_handle_packet(ctx, data, st, pkt, timestamp, buf, len,
@@ -133,7 +133,7 @@ static int h263_handle_packet(AVFormatContext *ctx, PayloadContext *data,
         /* Check the picture start code, only start buffering a new frame
          * if this is correct */
         if (len > 4 && AV_RB32(buf) >> 10 == 0x20) {
-            int ret = avio_open_dyn_buf(&data->buf);
+            ret = avio_open_dyn_buf(&data->buf);
             if (ret < 0)
                 return ret;
             data->timestamp = *timestamp;
@@ -185,13 +185,11 @@ static int h263_handle_packet(AVFormatContext *ctx, PayloadContext *data,
         avio_w8(data->buf, data->endbyte);
     data->endbyte_bits = 0;
 
-    av_init_packet(pkt);
-    pkt->size         = avio_close_dyn_buf(data->buf, &pkt->data);
-    pkt->destruct     = av_destruct_packet;
-    pkt->stream_index = st->index;
+    ret = ff_rtp_finalize_packet(pkt, &data->buf, st->index);
+    if (ret < 0)
+        return ret;
     if (!i)
         pkt->flags   |= AV_PKT_FLAG_KEY;
-    data->buf = NULL;
 
     return 0;
 }
diff --git a/libavformat/rtpdec_jpeg.c b/libavformat/rtpdec_jpeg.c
index fb68de9702..447dd361bc 100644
--- a/libavformat/rtpdec_jpeg.c
+++ b/libavformat/rtpdec_jpeg.c
@@ -20,6 +20,7 @@
  */
 
 #include "avformat.h"
+#include "rtpdec.h"
 #include "rtpdec_formats.h"
 #include "libavutil/intreadwrite.h"
 #include "libavcodec/mjpeg.h"
@@ -367,19 +368,11 @@ static int jpeg_parse_packet(AVFormatContext *ctx, PayloadContext *jpeg,
         avio_write(jpeg->frame, buf, sizeof(buf));
 
         /* Prepare the JPEG packet. */
-        av_init_packet(pkt);
-        pkt->size = avio_close_dyn_buf(jpeg->frame, &pkt->data);
-        if (pkt->size < 0) {
+        if ((ret = ff_rtp_finalize_packet(pkt, &jpeg->frame, st->index)) < 0) {
             av_log(ctx, AV_LOG_ERROR,
                    "Error occured when getting frame buffer.\n");
-            jpeg->frame = NULL;
-            return pkt->size;
+            return ret;
         }
-        pkt->stream_index = st->index;
-        pkt->destruct     = av_destruct_packet;
-
-        /* Re-init the frame buffer. */
-        jpeg->frame = NULL;
 
         return 0;
     }
diff --git a/libavformat/rtpdec_svq3.c b/libavformat/rtpdec_svq3.c
index 99c4c52dee..779ad8a42b 100644
--- a/libavformat/rtpdec_svq3.c
+++ b/libavformat/rtpdec_svq3.c
@@ -97,12 +97,11 @@ static int svq3_parse_packet (AVFormatContext *s, PayloadContext *sv,
     avio_write(sv->pktbuf, buf, len);
 
     if (end_packet) {
-        av_init_packet(pkt);
-        pkt->stream_index = st->index;
+        int ret = ff_rtp_finalize_packet(pkt, &sv->pktbuf, st->index);
+        if (ret < 0)
+            return ret;
+
         *timestamp        = sv->timestamp;
-        pkt->size         = avio_close_dyn_buf(sv->pktbuf, &pkt->data);
-        pkt->destruct     = av_destruct_packet;
-        sv->pktbuf        = NULL;
         return 0;
     }
 
diff --git a/libavformat/rtpdec_vp8.c b/libavformat/rtpdec_vp8.c
index aef5f78132..1edc152a48 100644
--- a/libavformat/rtpdec_vp8.c
+++ b/libavformat/rtpdec_vp8.c
@@ -36,15 +36,6 @@ struct PayloadContext {
     uint32_t       timestamp;
 };
 
-static void prepare_packet(AVPacket *pkt, PayloadContext *vp8, int stream)
-{
-    av_init_packet(pkt);
-    pkt->stream_index = stream;
-    pkt->size         = avio_close_dyn_buf(vp8->data, &pkt->data);
-    pkt->destruct     = av_destruct_packet;
-    vp8->data         = NULL;
-}
-
 static int vp8_handle_packet(AVFormatContext *ctx,
                              PayloadContext *vp8,
                              AVStream *st,
@@ -54,16 +45,14 @@ static int vp8_handle_packet(AVFormatContext *ctx,
                              int len, int flags)
 {
     int start_partition, end_packet;
-    int extended_bits, non_ref, part_id;
+    int extended_bits, part_id;
     int pictureid_present = 0, tl0picidx_present = 0, tid_present = 0,
         keyidx_present = 0;
-    int pictureid = -1, keyidx = -1;
 
     if (len < 1)
         return AVERROR_INVALIDDATA;
 
     extended_bits   = buf[0] & 0x80;
-    non_ref         = buf[0] & 0x20;
     start_partition = buf[0] & 0x10;
     part_id         = buf[0] & 0x0f;
     end_packet      = flags & RTP_FLAG_MARKER;
@@ -80,19 +69,12 @@ static int vp8_handle_packet(AVFormatContext *ctx,
         len--;
     }
     if (pictureid_present) {
+        int size;
         if (len < 1)
             return AVERROR_INVALIDDATA;
-        if (buf[0] & 0x80) {
-            if (len < 2)
-                return AVERROR_INVALIDDATA;
-            pictureid = AV_RB16(buf) & 0x7fff;
-            buf += 2;
-            len -= 2;
-        } else {
-            pictureid = buf[0] & 0x7f;
-            buf++;
-            len--;
-        }
+        size = buf[0] & 0x80 ? 2 : 1;
+        buf += size;
+        len -= size;
     }
     if (tl0picidx_present) {
         // Ignoring temporal level zero index
@@ -100,11 +82,7 @@ static int vp8_handle_packet(AVFormatContext *ctx,
         len--;
     }
     if (tid_present || keyidx_present) {
-        // Ignoring temporal layer index and layer sync bit
-        if (len < 1)
-            return AVERROR_INVALIDDATA;
-        if (keyidx_present)
-            keyidx = buf[0] & 0x1f;
+        // Ignoring temporal layer index, layer sync bit and keyframe index
         buf++;
         len--;
     }
@@ -133,7 +111,9 @@ static int vp8_handle_packet(AVFormatContext *ctx,
     avio_write(vp8->data, buf, len);
 
     if (end_packet) {
-        prepare_packet(pkt, vp8, st->index);
+        int ret = ff_rtp_finalize_packet(pkt, &vp8->data, st->index);
+        if (ret < 0)
+            return ret;
         return 0;
     }
 
diff --git a/libavformat/rtpdec_xiph.c b/libavformat/rtpdec_xiph.c
index 773f4aa391..ad24c2671a 100644
--- a/libavformat/rtpdec_xiph.c
+++ b/libavformat/rtpdec_xiph.c
@@ -201,20 +201,13 @@ static int xiph_handle_packet(AVFormatContext * ctx,
 
         if (fragmented == 3) {
             // end of xiph data packet
-            av_init_packet(pkt);
-            pkt->size = avio_close_dyn_buf(data->fragment, &pkt->data);
-
-            if (pkt->size < 0) {
+            int ret = ff_rtp_finalize_packet(pkt, &data->fragment, st->index);
+            if (ret < 0) {
                 av_log(ctx, AV_LOG_ERROR,
                        "Error occurred when getting fragment buffer.");
-                return pkt->size;
+                return ret;
             }
 
-            pkt->stream_index = st->index;
-            pkt->destruct = av_destruct_packet;
-
-            data->fragment = NULL;
-
             return 0;
         }
     }