Add session metadata for video stream

Introduce a new packet type, a "session" packet, containing metadata
about the encoding session. It is used only for the video stream,
and currently includes the video resolution.

For illustration, here is a sequence of packets on the video stream:

                                        device rotation
                                        v
    CODEC | SESSION | MEDIA | MEDIA | … | SESSION | MEDIA | MEDIA | …
           1920x1080 <-----------------> 1080x1920 <------------------
                      encoding session 1            encoding session 2

This metadata is not strictly necessary, since the video resolution can
be determined after decoding. However, it allows detection of cases
where the encoder does not respect the requested size (and logs a
warning), even without decoding (e.g., when there is no video playback).

Additional metadata could be added later if necessary, for example the
actual device rotation.

Refs #5918 <https://github.com/Genymobile/scrcpy/pull/5918>
Refs #5894 <https://github.com/Genymobile/scrcpy/pull/5894>

Co-authored-by: gz0119 <liyong2@4399.com>
This commit is contained in:
Romain Vimont
2025-05-10 10:23:02 +02:00
parent 0b4c94056c
commit 00e4800b0c
15 changed files with 240 additions and 82 deletions

View File

@@ -10,14 +10,15 @@
#define DOWNCAST(SINK) container_of(SINK, struct sc_decoder, packet_sink)
static bool
sc_decoder_open(struct sc_decoder *decoder, AVCodecContext *ctx) {
sc_decoder_open(struct sc_decoder *decoder, AVCodecContext *ctx,
const struct sc_stream_session *session) {
decoder->frame = av_frame_alloc();
if (!decoder->frame) {
LOG_OOM();
return false;
}
if (!sc_frame_source_sinks_open(&decoder->frame_source, ctx)) {
if (!sc_frame_source_sinks_open(&decoder->frame_source, ctx, session)) {
av_frame_free(&decoder->frame);
return false;
}
@@ -74,9 +75,16 @@ sc_decoder_push(struct sc_decoder *decoder, const AVPacket *packet) {
}
static bool
sc_decoder_packet_sink_open(struct sc_packet_sink *sink, AVCodecContext *ctx) {
sc_decoder_push_session(struct sc_decoder *decoder,
const struct sc_stream_session *session) {
return sc_frame_source_sinks_push_session(&decoder->frame_source, session);
}
static bool
sc_decoder_packet_sink_open(struct sc_packet_sink *sink, AVCodecContext *ctx,
const struct sc_stream_session *session) {
struct sc_decoder *decoder = DOWNCAST(sink);
return sc_decoder_open(decoder, ctx);
return sc_decoder_open(decoder, ctx, session);
}
static void
@@ -92,6 +100,14 @@ sc_decoder_packet_sink_push(struct sc_packet_sink *sink,
return sc_decoder_push(decoder, packet);
}
static bool
sc_decoder_packet_sink_push_session(struct sc_packet_sink *sink,
const struct sc_stream_session *session) {
struct sc_decoder *decoder = DOWNCAST(sink);
return sc_decoder_push_session(decoder, session);
}
void
sc_decoder_init(struct sc_decoder *decoder, const char *name) {
decoder->name = name; // statically allocated
@@ -101,6 +117,7 @@ sc_decoder_init(struct sc_decoder *decoder, const char *name) {
.open = sc_decoder_packet_sink_open,
.close = sc_decoder_packet_sink_close,
.push = sc_decoder_packet_sink_push,
.push_session = sc_decoder_packet_sink_push_session,
};
decoder->packet_sink.ops = &ops;