MT#56471 add flag to suppress early media

Track audio writes in the mix buffer to set the `active` flag to true
whenever a write occurs, which makes it possible to create the buffer in
an inactivate state and implicitly set it active on demand.

Handle the mix buffer not returning any data in the RTP sending logic
(which is what happens for an inactive buffer) by simply not sending any
packets.

Change-Id: Iaeb0f6deadb3d90020c8c62872735cc94db80504

daemon/audio_player.c

@@ -33,6 +33,12 @@ static bool audio_player_run(struct media_player *mp) {
 	unsigned int size;
 	void *buf = mix_buffer_read_fast(&ap->mb, ap->ptime, &size);
 	if (!buf) {
+		if (!size) {
+			// error or not active: just reschedule
+			timeval_add_usec(&mp->next_run, ap->ptime_us);
+			timerthread_obj_schedule_abs(&mp->tt_obj, &mp->next_run);
+			return false;
+		}
 		buf = g_alloca(size);
 		mix_buffer_read_slow(&ap->mb, buf, ap->ptime);
 	}
@@ -64,7 +70,6 @@ bool audio_player_setup(struct call_media *m, const struct rtp_payload_type *dst
 	unsigned int ptime_smp = ptime_ms * clockrate / 1000; // in samples
 
 	// TODO: shortcut this to avoid the detour of avframe -> avpacket -> avframe (all in s16)
-	// TODO: determine dest sample format from created encoder
 	struct rtp_payload_type src_pt = {
 		.payload_type = -1,
 		.encoding = STR_CONST_INIT("PCM-S16LE"), // XXX support flp
@@ -121,7 +126,8 @@ bool audio_player_setup(struct call_media *m, const struct rtp_payload_type *dst
 
 	bufsize_ms = MAX(bufsize_ms, ptime_ms * 2); // make sure the buf size is at least 2 frames
 
-	mix_buffer_init(&ap->mb, AV_SAMPLE_FMT_S16, clockrate, dst_pt->channels, bufsize_ms, delay_ms);
+	mix_buffer_init_active(&ap->mb, AV_SAMPLE_FMT_S16, clockrate, dst_pt->channels, bufsize_ms, delay_ms,
+			false);
 
 	return true;
 
@@ -131,6 +137,16 @@ error:
 }
 
 
+void audio_player_activate(struct call_media *m) {
+	if (!m)
+		return;
+	struct audio_player *ap = m->audio_player;
+	if (!ap)
+		return;
+	mix_buffer_activate(&ap->mb);
+}
+
+
 // call locked in W
 void audio_player_start(struct call_media *m) {
 	struct audio_player *ap;

daemon/call.c

@@ -2759,6 +2759,9 @@ void codecs_offer_answer(struct call_media *media, struct call_media *other_medi
 			set_transcoding_flag(media->monologue, other_media->monologue, true);
 		if (codec_handlers_update(other_media, media, NULL, NULL))
 			set_transcoding_flag(other_media->monologue, media->monologue, true);
+
+		// activate audio player if needed (not done by codec_handlers_update without `flags`)
+		audio_player_activate(media);
 	}
 }
 

daemon/call_interfaces.c

@@ -975,6 +975,9 @@ static void call_ng_flags_flags(struct sdp_ng_flags *out, str *s, void *dummy) {
 		case CSH_LOOKUP("reset"):
 			out->reset = 1;
 			break;
+		case CSH_LOOKUP("early-media"):
+			out->early_media = 1;
+			break;
 		case CSH_LOOKUP("all"):
 			out->all = ALL_ALL;
 			break;

daemon/codec.c

@@ -1438,6 +1438,8 @@ next:
 
 			audio_player_setup(sink, pref_dest_codec, rtpe_config.audio_buffer_length,
 					rtpe_config.audio_buffer_delay);
+			if (flags && (flags->early_media || flags->opmode == OP_ANSWER))
+				audio_player_activate(sink);
 		}
 	}
 

docs/ng_control_protocol.md

@@ -805,6 +805,14 @@ Spaces in each string may be replaced by hyphens.
 	the DSP to detect in-band DTMF audio tones even when it
 	wouldn't otherwise be necessary.
 
+* `early media`
+
+    Used in conjunction with the audio player. If set, audio playback is
+    started immediately when processing an `offer` message. The default
+    behaviour is to start the audio player only after the `answer` has been
+    processed, or when any audio to be played back has actually been received
+    (either from another party to the call, or via the `play media` command).
+
 * `full rtcp attribute`
 
 	Include the full version of the `a=rtcp` line (complete with network address) instead of

include/audio_player.h

@@ -22,6 +22,7 @@ struct rtp_payload_type;
 
 bool audio_player_setup(struct call_media *, const struct rtp_payload_type *,
 		unsigned int size_ms, unsigned int delay_ms);
+void audio_player_activate(struct call_media *);
 void audio_player_free(struct call_media *);
 
 void audio_player_start(struct call_media *);
@@ -36,6 +37,7 @@ void audio_player_add_frame(struct audio_player *, uint32_t ssrc, AVFrame *);
 INLINE void audio_player_start(struct call_media *m) { }
 INLINE void audio_player_free(struct call_media *m) { }
 INLINE void audio_player_stop(struct call_media *m) { }
+INLINE void audio_player_activate(struct call_media *m) { }
 
 #endif
 

include/call_interfaces.h

@@ -162,6 +162,7 @@ struct sdp_ng_flags {
 	             single_codec:1,
 		     reuse_codec:1,
 		     allow_transcoding:1,
+		     early_media:1,
 		     accept_any:1,
 	             inject_dtmf:1,
 		     detect_dtmf:1,

lib/mix_buffer.c

@@ -73,8 +73,8 @@ static void fill_up_to(struct mix_buffer *mb, unsigned int up_to) {
 void *mix_buffer_read_fast(struct mix_buffer *mb, unsigned int samples, unsigned int *size) {
 	LOCK(&mb->lock);
 
-	if (samples > mb->size) {
-		*size = 0; // error
+	if (samples > mb->size || !mb->active) {
+		*size = 0; // error or inactive
 		return NULL;
 	}
 
@@ -245,6 +245,8 @@ bool mix_buffer_write_delay(struct mix_buffer *mb, uint32_t ssrc, const void *bu
 	if (created)
 		mix_buff_src_shift_delay(mb, src, last, now);
 
+	mb->active = true;
+
 	// loop twice at the most to re-run logic after a reset
 	while (true) {
 		// shortcut if we're at the write head
@@ -284,8 +286,8 @@ static struct ssrc_entry *mix_buffer_ssrc_new(void *p) {
 
 
 // struct must be zeroed already
-bool mix_buffer_init(struct mix_buffer *mb, enum AVSampleFormat fmt, unsigned int clockrate,
-		unsigned int channels, unsigned int size_ms, unsigned int delay_ms)
+bool mix_buffer_init_active(struct mix_buffer *mb, enum AVSampleFormat fmt, unsigned int clockrate,
+		unsigned int channels, unsigned int size_ms, unsigned int delay_ms, bool active)
 {
 	switch (fmt) {
 		case AV_SAMPLE_FMT_S16:
@@ -305,6 +307,7 @@ bool mix_buffer_init(struct mix_buffer *mb, enum AVSampleFormat fmt, unsigned in
 	mb->clockrate = clockrate;
 	mb->channels = channels;
 	mb->delay = delay;
+	mb->active = active;
 
 	mb->ssrc_hash = create_ssrc_hash_full_fast(mix_buffer_ssrc_new, mb);
 

lib/mix_buffer.h

@@ -50,6 +50,7 @@ struct mix_buffer {
 	unsigned int delay; // initial write delay for new inputs/sources
 
 	unsigned int loops; // how many times the write pos has circled around
+	bool active; // to optionally suppress early media
 
 	// implementation details
 	const struct mix_buffer_impl *impl;
@@ -58,8 +59,14 @@ struct mix_buffer {
 };
 
 
-bool mix_buffer_init(struct mix_buffer *, enum AVSampleFormat, unsigned int clockrate,
-		unsigned int channels, unsigned int size_ms, unsigned int delay_ms);
+bool mix_buffer_init_active(struct mix_buffer *, enum AVSampleFormat, unsigned int clockrate,
+		unsigned int channels, unsigned int size_ms, unsigned int delay_ms, bool active);
+#define mix_buffer_init(mb, fmt, clockrate, channels, size_ms, delay_ms) \
+	mix_buffer_init_active(mb, fmt, clockrate, channels, size_ms, delay_ms, true)
+INLINE void mix_buffer_activate(struct mix_buffer *mb) {
+	LOCK(&mb->lock);
+	mb->active = true;
+}
 void mix_buffer_destroy(struct mix_buffer *);
 
 void *mix_buffer_read_fast(struct mix_buffer *, unsigned int samples, unsigned int *size);

utils/rtpengine-ng-client

@@ -49,6 +49,7 @@ my @flags = qw(
 	passthrough
 	no-passthrough
 	pause
+	early-media
 );
 
 my @string_opts = qw(