Handle padded audio packets correctly

webrtc/modules/rtp_rtcp/source/rtp_receiver_audio.cc

 /*
  *  Copyright (c) 2012 The WebRTC project authors. All Rights Reserved.
  *
  *  Use of this source code is governed by a BSD-style license
  *  that can be found in the LICENSE file in the root of the source
  *  tree. An additional intellectual property rights grant can be found
  *  in the file PATENTS.  All contributing project authors may
  *  be found in the AUTHORS file in the root of the source tree.
  */
 
@@ skipping 194 matching lines @@
   return 0;
 }
 
 // We are not allowed to have any critsects when calling data_callback.
 int32_t RTPReceiverAudio::ParseAudioCodecSpecific(
     WebRtcRTPHeader* rtp_header,
     const uint8_t* payload_data,
     size_t payload_length,
     const AudioPayload& audio_specific,
     bool is_red) {
-
   if (payload_length == 0) {

[minyue-webrtc, 2017/05/10 13:03:18]

I tried it, and I am afraid OnReceivedPayloadData(nullptr, 0) will never be
called.

For a quick hack, you need if (payload_length ==
rtp_header->header.paddingLength)

But this put me into great doubt about how the whole padding should work with
neteq. We should be receiving some garbage for current implementation (I
actually hear some burst of noise in video_loopback test and wondered why)

-    return 0;
+    rtp_header->type.Audio.isCNG = false;
+    rtp_header->frameType = kEmptyFrame;
+    return data_callback_->OnReceivedPayloadData(nullptr, 0, rtp_header);
   }
 
   bool telephone_event_packet =
       TelephoneEventPayloadType(rtp_header->header.payloadType);
   if (telephone_event_packet) {
     rtc::CritScope lock(&crit_sect_);
 
     // RFC 4733 2.3
     // 0                   1                   2                   3
     // 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
     // +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
     // |     event     |E|R| volume    |          duration             |
     // +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
     //
     if (payload_length % 4 != 0) {
       return -1;
     }
     size_t number_of_events = payload_length / 4;
 
     // sanity
     if (number_of_events >= MAX_NUMBER_OF_PARALLEL_TELEPHONE_EVENTS) {
       number_of_events = MAX_NUMBER_OF_PARALLEL_TELEPHONE_EVENTS;
     }
     for (size_t n = 0; n < number_of_events; ++n) {
+      RTC_DCHECK_GE(payload_length, (4 * n) + 2);
       bool end = (payload_data[(4 * n) + 1] & 0x80) ? true : false;
 
       std::set<uint8_t>::iterator event =
           telephone_event_reported_.find(payload_data[4 * n]);
 
       if (event != telephone_event_reported_.end()) {
         // we have already seen this event
         if (end) {
           telephone_event_reported_.erase(payload_data[4 * n]);
         }
@@ skipping 32 matching lines @@
       }
       std::set<uint8_t>::iterator first =
           telephone_event_reported_.begin();
       if (first != telephone_event_reported_.end() && *first > 15) {
         // don't forward non DTMF events
         return 0;
       }
     }
   }
   // TODO(holmer): Break this out to have RED parsing handled generically.
+  RTC_DCHECK_GT(payload_length, 0);
   if (is_red && !(payload_data[0] & 0x80)) {
     // we recive only one frame packed in a RED packet remove the RED wrapper
     rtp_header->header.payloadType = payload_data[0];
 
     // only one frame in the RED strip the one byte to help NetEq
     return data_callback_->OnReceivedPayloadData(
         payload_data + 1, payload_length - 1, rtp_header);
   }
 
   rtp_header->type.Audio.channel = audio_specific.channels;
   return data_callback_->OnReceivedPayloadData(
       payload_data, payload_length, rtp_header);
 }
 }  // namespace webrtc