DAEMON-PPS: synthesise H.264 SPS/PPS NAL units from V4L2 controls
libva-v4l2-request-fourier (and any V4L2-stateless-API consumer)
passes H.264 SPS/PPS as separate V4L2_CID_STATELESS_H264_{SPS,PPS}
controls; only the slice NAL goes into the OUTPUT buffer. This is
correct per the V4L2 stateless contract. But libavcodec — which
the daedalus daemon uses for actual decode (Option γ) — wants a
self-contained AnnexB stream including SPS+PPS before any slice.
Result on higgs: "non-existing PPS 0 referenced" + decode_slice_
header errors on every H.264 frame, even after LIBVA-1 and -2
routing correctly delivered the request to the daemon.
Fix splits across kernel + daemon, keeping the kernel module as a
thin transport and putting the actual NAL encoding in userspace:
include/daedalus_v4l2_proto.h:
Add struct daedalus_h264_meta (the four v4l2_ctrl_h264_*
structs the kernel collects) and DAEDALUS_REQ_FLAG_H264_META
(set in req.flags when the meta block is present between the
daedalus_req_decode prefix and the slice bitstream).
kernel/daedalus_v4l2_main.c:
Add daedalus_collect_h264_meta() — reads the H.264 ctrl values
from the bound media_request via v4l2_ctrl_find +
ctrl->p_cur.p_h264_*. device_run() calls it on H.264 codec_id,
copies the structs into the REQ_DECODE payload between the
prefix and bitstream, and sets the flag. Payload size is
bounds-checked against DAEDALUS_PROTO_MAX_PAYLOAD so an over-
sized slice + meta fails loud instead of truncating.
daemon/src/bitstream_writer.{c,h}:
New module — MSB-first bit packer with H.264 Exp-Golomb ue(v)
and se(v) coding + rbsp_trailing_bits alignment. Sticky
overflow flag so callers can verify the output buffer wasn't
truncated.
daemon/src/h264_nal_synth.{c,h}:
New module — turns v4l2_ctrl_h264_sps / v4l2_ctrl_h264_pps
into AnnexB-framed NAL units per ITU-T H.264 7.3.2.1 / 7.3.2.2.
Emits emulation prevention bytes (0x03 after every 00 00 in the
EBSP) and the 4-byte start code (0x00000001). Coverage matches
what V4L2 stateless surface gives us: VUI parameters and full
scaling matrices are NOT emitted (V4L2 doesn't carry them — the
seq_scaling_matrix_present_flag is set to 0 and libavcodec uses
flat defaults, which matches the de-facto behaviour of most
H.264 streams libva-v4l2-request drives).
daemon/src/decoder.c:
daedalus_decoder_run_request() now takes an optional
h264_meta parameter. For codec_id == H264 with meta != NULL,
synthesises SPS+PPS NAL units, allocates a combined
[SPS][PPS][slice] buffer (+ AV_INPUT_BUFFER_PADDING_SIZE), and
feeds that to avcodec_send_packet instead of the raw slice.
VP9/AV1 path unchanged (frames are self-contained). Cleanup
now goes through a unified `out:` label so the assembled
buffer is always freed on every exit (including the existing
decoder_open_codec / no-frame / receive_frame failure paths).
daemon/src/chardev_client.c:
handle_req_decode() peels off the optional meta block when the
flag is set, passes it through to the decoder, and updates
the payload-length consistency check (now allows for an extra
sizeof(daedalus_h264_meta) when the flag is on).
Build (boltzmann aarch64): clean compile of all daemon sources,
including bitstream_writer + h264_nal_synth + the refactored
decoder.c. Kernel module compile to be verified via DKMS rebuild
on higgs in the marfrit-packages bump that follows.
Test plan: with this commit + a marfrit-packages daedalus pin
bump, higgs's ffmpeg -hwaccel vaapi -i h264_test.mp4 should
produce a successful decode (vs. the previous "non-existing PPS 0
referenced" failure). The daemon log should show:
decoder: opened h264 context
decoder: h264 prepended SPS=NB PPS=MB slice=KB
decoder: OK 320x240 fmt=0 (yuv420p) fnv1a=0x...
VP9 / AV1 behaviour unchanged — they don't carry meta and the
existing per-frame self-describing path still applies.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -25,6 +25,7 @@
|
||||
#define DAEDALUS_V4L2_PROTO_H
|
||||
|
||||
#include <linux/types.h>
|
||||
#include <linux/v4l2-controls.h>
|
||||
|
||||
#define DAEDALUS_PROTO_MAGIC 0x44303456u /* 'D04V' */
|
||||
#define DAEDALUS_PROTO_VERSION 0u /* pre-1.0 */
|
||||
@@ -90,10 +91,22 @@ enum daedalus_codec_id {
|
||||
DAEDALUS_CODEC_H264 = 3,
|
||||
};
|
||||
|
||||
/**
|
||||
* DAEDALUS_REQ_FLAG_H264_META - daedalus_req_decode.flags bit
|
||||
*
|
||||
* Set when a struct daedalus_h264_meta is present between the
|
||||
* daedalus_req_decode prefix and the slice bitstream. Required for
|
||||
* H.264 (codec_id == DAEDALUS_CODEC_H264) since libavcodec needs
|
||||
* SPS/PPS that the V4L2 stateless API delivers as separate ctrls,
|
||||
* not in the OUTPUT buffer. Other codecs ignore this bit.
|
||||
*/
|
||||
#define DAEDALUS_REQ_FLAG_H264_META 0x00000001u
|
||||
|
||||
/**
|
||||
* struct daedalus_req_decode - REQ_DECODE payload prefix
|
||||
* @codec_id: enum daedalus_codec_id
|
||||
* @bitstream_len: bytes of bitstream following this struct
|
||||
* (after any optional metadata blocks — see flags)
|
||||
* @capture_width: CAPTURE buffer width in pixels
|
||||
* @capture_height: CAPTURE buffer height in pixels
|
||||
* @capture_pix_fmt: V4L2 fourcc of the CAPTURE format
|
||||
@@ -103,10 +116,17 @@ enum daedalus_codec_id {
|
||||
* @capture_plane_size: per-plane sizeimage from V4L2 S_FMT
|
||||
* (plane[0..N-1]). Unused entries = 0.
|
||||
* @capture_plane_stride: per-plane bytesperline from V4L2 S_FMT.
|
||||
* @flags: reserved, must be zero
|
||||
* @flags: bitmask of DAEDALUS_REQ_FLAG_*
|
||||
*
|
||||
* Total payload_len for a REQ_DECODE = sizeof(struct
|
||||
* daedalus_req_decode) + bitstream_len.
|
||||
* Wire layout for a REQ_DECODE payload:
|
||||
*
|
||||
* struct daedalus_req_decode req;
|
||||
* IF (req.flags & DAEDALUS_REQ_FLAG_H264_META):
|
||||
* struct daedalus_h264_meta meta;
|
||||
* u8 bitstream[req.bitstream_len];
|
||||
*
|
||||
* Total payload_len = sizeof(req) + (meta ? sizeof(meta) : 0)
|
||||
* + req.bitstream_len.
|
||||
*
|
||||
* The daemon uses (capture_*) to fetch + mmap the right CAPTURE
|
||||
* plane via DAEDALUS_IOC_GET_DMABUF, then decodes pixels
|
||||
@@ -124,6 +144,32 @@ struct daedalus_req_decode {
|
||||
__u32 flags;
|
||||
};
|
||||
|
||||
/**
|
||||
* struct daedalus_h264_meta - H.264 stateless-decode metadata
|
||||
*
|
||||
* Optional block following the daedalus_req_decode prefix when
|
||||
* DAEDALUS_REQ_FLAG_H264_META is set in req.flags. Carries the
|
||||
* structured controls the kernel collected from
|
||||
* V4L2_CID_STATELESS_H264_* — the daemon converts them into
|
||||
* AnnexB SPS+PPS NAL units (via an Exp-Golomb writer) and
|
||||
* prepends those NAL units to the slice bitstream before
|
||||
* handing it to libavcodec.
|
||||
*
|
||||
* The kernel never inspects these fields beyond capturing them
|
||||
* verbatim from the v4l2_ctrl_handler at device_run time; the
|
||||
* field semantics are governed entirely by the linux uABI
|
||||
* V4L2 stateless H.264 control definitions.
|
||||
*
|
||||
* Wire-stable across phases. If the kernel V4L2 H.264 control
|
||||
* structs grow new fields the protocol version bumps with them.
|
||||
*/
|
||||
struct daedalus_h264_meta {
|
||||
struct v4l2_ctrl_h264_sps sps;
|
||||
struct v4l2_ctrl_h264_pps pps;
|
||||
struct v4l2_ctrl_h264_scaling_matrix scaling_matrix;
|
||||
struct v4l2_ctrl_h264_decode_params decode_params;
|
||||
};
|
||||
|
||||
/**
|
||||
* enum daedalus_decode_status - RESP_FRAME outcome codes
|
||||
* @DAEDALUS_DECODE_OK: frame produced; fields below populated
|
||||
|
||||
Reference in New Issue
Block a user