marfrit
8c1d9960c4
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>
102 lines
2.1 KiB
C
102 lines
2.1 KiB
C
/* SPDX-License-Identifier: BSD-2-Clause */
|
|
#include "bitstream_writer.h"
|
|
|
|
#include <string.h>
|
|
|
|
void bsw_init(struct bs_writer *bs, uint8_t *buf, size_t cap)
|
|
{
|
|
bs->buf = buf;
|
|
bs->cap = cap;
|
|
bs->pos_bytes = 0;
|
|
bs->pos_bit = 0;
|
|
bs->overflow = false;
|
|
if (buf && cap)
|
|
buf[0] = 0;
|
|
}
|
|
|
|
void bsw_put_u(struct bs_writer *bs, uint32_t v, int n)
|
|
{
|
|
int i;
|
|
|
|
if (n <= 0 || n > 32)
|
|
return;
|
|
|
|
for (i = n - 1; i >= 0; i--) {
|
|
uint8_t bit = (uint8_t) ((v >> i) & 1u);
|
|
|
|
if (bs->pos_bytes >= bs->cap) {
|
|
bs->overflow = true;
|
|
return;
|
|
}
|
|
|
|
if (bs->pos_bit == 0)
|
|
bs->buf[bs->pos_bytes] = 0;
|
|
|
|
bs->buf[bs->pos_bytes] |= (uint8_t) (bit << (7 - bs->pos_bit));
|
|
bs->pos_bit++;
|
|
if (bs->pos_bit == 8) {
|
|
bs->pos_bit = 0;
|
|
bs->pos_bytes++;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Exp-Golomb ue(v) — H.264 9.1 / 9.1.1.
|
|
* For an unsigned value v:
|
|
* codeNum = v
|
|
* leadingZeroBits = floor(log2(codeNum + 1))
|
|
* code = leadingZeroBits zeros, then '1', then leadingZeroBits bits
|
|
* of (codeNum + 1 - 2^leadingZeroBits)
|
|
*
|
|
* Total length = 2 * leadingZeroBits + 1 bits. For v = 0 the
|
|
* code is just "1" (1 bit). For v in [1,2] the code is 3 bits, etc.
|
|
*/
|
|
void bsw_put_ue(struct bs_writer *bs, uint32_t v)
|
|
{
|
|
uint32_t code_num = v;
|
|
uint32_t code_num_plus_1 = code_num + 1u;
|
|
int leading_zeros = 0;
|
|
uint32_t tmp;
|
|
|
|
tmp = code_num_plus_1 >> 1;
|
|
while (tmp) {
|
|
leading_zeros++;
|
|
tmp >>= 1;
|
|
}
|
|
|
|
/* leading_zeros zero bits */
|
|
bsw_put_u(bs, 0u, leading_zeros);
|
|
/* one '1' bit + the (leading_zeros) low bits of code_num_plus_1 */
|
|
bsw_put_u(bs, code_num_plus_1, leading_zeros + 1);
|
|
}
|
|
|
|
/*
|
|
* Exp-Golomb se(v) — H.264 9.1.1: signed mapping is interleaved:
|
|
* 0 -> 0, 1 -> 1, -1 -> 2, 2 -> 3, -2 -> 4, ...
|
|
* i.e. codeNum = 2 * |v| - (v > 0 ? 1 : 0).
|
|
*/
|
|
void bsw_put_se(struct bs_writer *bs, int32_t v)
|
|
{
|
|
uint32_t code_num;
|
|
|
|
if (v > 0)
|
|
code_num = (uint32_t) (2 * v - 1);
|
|
else
|
|
code_num = (uint32_t) (-2 * v);
|
|
bsw_put_ue(bs, code_num);
|
|
}
|
|
|
|
void bsw_align_rbsp(struct bs_writer *bs)
|
|
{
|
|
/* rbsp_stop_one_bit + zero-fill to byte boundary */
|
|
bsw_put_u(bs, 1u, 1);
|
|
while (bs->pos_bit != 0)
|
|
bsw_put_u(bs, 0u, 1);
|
|
}
|
|
|
|
size_t bsw_bytes(const struct bs_writer *bs)
|
|
{
|
|
return bs->pos_bytes;
|
|
}
|