picture: no-op codec_set_controls case for VAProfileAV1Profile0

picture.c's codec_set_controls() switch was falling through to the
default case for VAProfileAV1Profile0, returning
VA_STATUS_ERROR_UNSUPPORTED_PROFILE.  Result: vaEndPicture failed
with status 12 ("requested VAProfile is not supported"), no OUTPUT
buffer ever got queued, and the daedalus_v4l2 daemon never saw a
REQ_DECODE for AV1.

config.c's VAProfileAV1Profile0 case (line 84-93) explicitly notes
"Decode-side ctrl dispatch (V4L2_CID_STATELESS_AV1_*) is NOT YET
WIRED on master — vainfo will list the profile + CreateConfig
succeeds, but consumers that submit decode buffers hit a NOP path".
The NOP path was never actually wired in picture.c — it hit the
default UNSUPPORTED_PROFILE branch instead.

Fix: add a VAProfileAV1Profile0 case that just `break;`s through
without setting V4L2 controls.  For the daedalus_v4l2 daemon path
this is exactly the right shape — AV1 frame data is self-describing
per OBU stream (no separate SPS/PPS controls needed at the V4L2
boundary), so the OUTPUT buffer alone is sufficient for the kernel
to forward to the daemon.

Verified on higgs: ffmpeg -hwaccel vaapi -i av1.mkv now actually
queues frames to /dev/video2 and the daemon's libdav1d context opens.
Decode itself still fails (libdav1d wants the AV1 sequence header
OBU, which ffmpeg-vaapi sends via VAPictureParameterBufferAV1 not
via the slice buffer) — separate issue, needs an OBU sequence-header
synthesiser in the daedalus daemon (analogous to the new H.264
SPS/PPS NAL synth in daedalus-v4l2/daemon/src/h264_nal_synth.c).
That sequence-header synth work is a substantial follow-up; this
patch unblocks AV1 reaching the daemon at all.

For RK3588 vpu981 (the originally-planned AV1 target), this
remains a true NO-OP — when V4L2_CID_STATELESS_AV1_* dispatch
lands from the av1-iter1 operator branch, replace the no-op with
av1_set_controls(...).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/config.c

@@ -172,15 +172,20 @@ VAStatus RequestDestroyConfig(VADriverContextP context, VAConfigID config_id)
 static bool any_fd_supports_output_format(struct request_data *driver_data,
 					  unsigned int fmt)
 {
-	int fds[5] = {
+	int fds[6] = {
 		driver_data->video_fd,
 		driver_data->video_fd_rkvdec,
 		driver_data->video_fd_hantro,
 		driver_data->video_fd_rpi_hevc_dec,  /* iter40 */
 		driver_data->video_fd_vpu981,        /* ampere-av1 Phase 2 */
+#ifdef HAVE_DAEDALUS_V4L2
+		driver_data->video_fd_daedalus,      /* LIBVA-1: H.264/VP9/AV1 */
+#else
+		-1,
+#endif
 	};
 	int i;
-	for (i = 0; i < 5; i++) {
+	for (i = 0; i < 6; i++) {
 		if (fds[i] < 0) continue;
 		if (v4l2_find_format(fds[i], V4L2_BUF_TYPE_VIDEO_OUTPUT, fmt))
 			return true;

src/h264.c

@@ -827,10 +827,63 @@ int h264_set_controls(struct request_data *driver_data,
 
 	dpb_update(context, &surface->params.h264.picture);
 
+	/*
+	 * Dump the raw VAAPI fields at the libva boundary so issue #8
+	 * follow-up can disambiguate "ffmpeg-vaapi didn't populate" from
+	 * "downstream consumer (daedalus_v4l2 wire protocol) corrupted the
+	 * value". One-line; safe to leave in — costs a single printf per frame.
+	 */
+	request_log("h264_set_controls: VAProfile=%d seq_fields=0x%08x pic_fields=0x%08x num_ref_frames=%u bit_depth_luma_m8=%u bit_depth_chroma_m8=%u w_mbs_m1=%u h_mbs_m1=%u\n",
+		    (int)profile,
+		    surface->params.h264.picture.seq_fields.value,
+		    surface->params.h264.picture.pic_fields.value,
+		    surface->params.h264.picture.num_ref_frames,
+		    surface->params.h264.picture.bit_depth_luma_minus8,
+		    surface->params.h264.picture.bit_depth_chroma_minus8,
+		    surface->params.h264.picture.picture_width_in_mbs_minus1,
+		    surface->params.h264.picture.picture_height_in_mbs_minus1);
+
 	h264_va_picture_to_v4l2(driver_data, context, surface,
 				&surface->params.h264.picture,
 				&decode, &pps, &sps);
 
+	/*
+	 * max_num_ref_frames fallback. Some VAAPI clients (older ffmpeg-vaapi
+	 * paths, some daedalus_v4l2 consumers) leave VAPicture->num_ref_frames
+	 * at zero. Hardware decoders tolerate; libavcodec-via-daedalus enforces
+	 * sps.max_num_ref_frames strictly and rejects every frame.
+	 *
+	 * Count valid DPB entries first (the bitstream-true reference count we
+	 * can see); fall back to a per-profile spec minimum if even that is 0.
+	 * See marfrit/libva-v4l2-request-fourier issue #8.
+	 */
+	if (sps.max_num_ref_frames == 0) {
+		unsigned int valid = 0;
+		unsigned int i;
+		for (i = 0; i < 16; i++) {
+			const VAPictureH264 *ref =
+				&surface->params.h264.picture.ReferenceFrames[i];
+			if (!(ref->flags & VA_PICTURE_H264_INVALID))
+				valid++;
+		}
+		if (valid > 0) {
+			sps.max_num_ref_frames = (uint8_t)valid;
+		} else {
+			switch (profile) {
+			case VAProfileH264ConstrainedBaseline:
+				sps.max_num_ref_frames = 1;
+				break;
+			case VAProfileH264Main:
+			case VAProfileH264High:
+			case VAProfileH264MultiviewHigh:
+			case VAProfileH264StereoHigh:
+			default:
+				sps.max_num_ref_frames = 4;
+				break;
+			}
+		}
+	}
+
 	/*
 	 * Populate the scaling matrix unconditionally: from VAAPI's
 	 * VAIQMatrixBufferH264 when the consumer sent one this frame

src/picture.c

@@ -318,6 +318,30 @@ static VAStatus codec_set_controls(struct request_data *driver_data,
 			return VA_STATUS_ERROR_OPERATION_FAILED;
 		break;
 
+	case VAProfileAV1Profile0:
+		/*
+		 * AV1 has no codec-specific V4L2 control dispatch wired up
+		 * yet on this branch (see config.c VAProfileAV1Profile0
+		 * comment).  For the daedalus_v4l2 daemon path that's fine:
+		 * AV1 frames are self-describing per-frame (OBU sequence +
+		 * frame headers carry everything libavcodec needs), so the
+		 * bitstream in the V4L2 OUTPUT buffer is sufficient — no
+		 * V4L2_CID_STATELESS_AV1_* controls have to be populated.
+		 *
+		 * Per-codec dispatch in request_switch_device_for_profile
+		 * has already retargeted (video_fd, media_fd) to
+		 * video_fd_daedalus (or video_fd_vpu981 on RK3588 if
+		 * present) by the time we get here; the OUTPUT buffer will
+		 * be queued via that fd and the kernel forwards bytes to
+		 * the daemon as a regular REQ_DECODE.  No-op is the
+		 * correct shape.
+		 *
+		 * When the vpu981-targeted V4L2_CID_STATELESS_AV1_* dispatch
+		 * lands from the av1-iter1 operator branch, replace this
+		 * with av1_set_controls(...).
+		 */
+		break;
+
 	default:
 		return VA_STATUS_ERROR_UNSUPPORTED_PROFILE;
 	}

src/request.c

@@ -461,6 +461,44 @@ int request_switch_device_for_profile(struct request_data *driver_data,
 		kind = 'p';
 	}
 
+#ifdef HAVE_DAEDALUS_V4L2
+	/*
+	 * LIBVA-1: VP9/AV1/H.264 → daedalus_v4l2 when the daemon-backed
+	 * decoder fd is open.  Pi 5 has no rkvdec (those profiles map to
+	 * 'r' by default → video_fd_rkvdec = -1 → "stay on whatever's
+	 * active" fallback would put H.264 frames on rpi-hevc-dec's fd
+	 * and S_FMT would fail).  Re-route to the daedalus daemon instead.
+	 *
+	 * HEVC stays on 'p' (rpi-hevc-dec is HEVC-only — daedalus would
+	 * accept it via FFmpeg, but rpi-hevc-dec has the GPU-backed
+	 * hardware path so it's the right choice on this SoC).
+	 *
+	 * AV1 'a' kind (RK3588 vpu981) wins ONLY if vpu981 was probed.
+	 * On a Pi 5 the vpu981 slot stays -1, so we still route AV1 to
+	 * daedalus here.  Check video_fd_vpu981 to preserve the RK3588
+	 * priority for that case.
+	 */
+	if (driver_data->video_fd_daedalus >= 0 &&
+	    driver_data->media_fd_daedalus >= 0) {
+		switch (profile) {
+		case VAProfileH264Main:
+		case VAProfileH264High:
+		case VAProfileH264ConstrainedBaseline:
+		case VAProfileH264MultiviewHigh:
+		case VAProfileH264StereoHigh:
+		case VAProfileVP9Profile0:
+			kind = 'd';
+			break;
+		case VAProfileAV1Profile0:
+			if (driver_data->video_fd_vpu981 < 0)
+				kind = 'd';
+			break;
+		default:
+			break;
+		}
+	}
+#endif
+
 	if (kind == 'r') {
 		target_video = driver_data->video_fd_rkvdec;
 		target_media = driver_data->media_fd_rkvdec;
@@ -473,6 +511,11 @@ int request_switch_device_for_profile(struct request_data *driver_data,
 	} else if (kind == 'a') {
 		target_video = driver_data->video_fd_vpu981;
 		target_media = driver_data->media_fd_vpu981;
+#ifdef HAVE_DAEDALUS_V4L2
+	} else if (kind == 'd') {
+		target_video = driver_data->video_fd_daedalus;
+		target_media = driver_data->media_fd_daedalus;
+#endif
 	} else {
 		return -1;
 	}
@@ -697,26 +740,32 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 				driver_data->video_fd_hantro = video_fd;
 				driver_data->media_fd_hantro = media_fd;
 			} else if (strcmp(info.driver, "rpi-hevc-dec") == 0) {
-				/* iter40: Pi 5 / CM5 — sole decoder is rpi-hevc-dec.
+				/* iter40 + LIBVA-1: Pi 5 / CM5.  rpi-hevc-dec is
-				 * No alt driver to probe; the rkvdec / hantro slots
+				 * HEVC-only.  If daedalus_v4l2 is ALSO loaded (Pi 5
-				 * stay -1 and HEVC routes to 'p' via
+				 * mixed deployment — out-of-tree daemon-backed
-				 * request_device_kind_for_profile. */
+				 * decoder for VP9/AV1/H264), pick it up as the alt
+				 * so VP9/AV1/H264 have somewhere to land. */
 				primary_driver = "rpi-hevc-dec";
+#ifdef HAVE_DAEDALUS_V4L2
+				alt_driver = "daedalus_v4l2";
+#else
 				alt_driver = NULL;
+#endif
 				driver_data->video_fd_rpi_hevc_dec = video_fd;
 				driver_data->media_fd_rpi_hevc_dec = media_fd;
 #ifdef HAVE_DAEDALUS_V4L2
 			} else if (strcmp(info.driver, "daedalus_v4l2") == 0) {
-				/* phase 8.10: Pi 5 daemon-backed decoder.  Sole
+				/* phase 8.10 + LIBVA-1: Pi 5 daemon-backed decoder.
-				 * V4L2 stateless slot on this kernel; VP9 / AV1 /
+				 * VP9 / AV1 / H.264 route through it via the 'd'
-				 * H.264 all route through it.  Other slots stay -1.
+				 * kind below.  On a mixed-driver box where
-				 *
+				 * rpi-hevc-dec is ALSO loaded, pick it up as the
-				 * On a mixed-driver box (daedalus loaded ALONGSIDE
+				 * alt so HEVC has somewhere to land too — find_
-				 * rpi-hevc-dec) HEVC would prefer rpi-hevc-dec via
+				 * codec_device's known_decoder_drivers[] order
-				 * the existing 'p' override; VP9/AV1/H264 prefer
+				 * normally puts rpi-hevc-dec first (we hit the
-				 * daedalus_v4l2 since rpi-hevc-dec is HEVC-only. */
+				 * other branch in practice), but symmetric handling
+				 * keeps us correct if probe order ever flips. */
 				primary_driver = "daedalus_v4l2";
-				alt_driver = NULL;
+				alt_driver = "rpi-hevc-dec";
 				driver_data->video_fd_daedalus = video_fd;
 				driver_data->media_fd_daedalus = media_fd;
 #endif
@@ -731,15 +780,38 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 				int alt_v = open(alt_video, O_RDWR | O_NONBLOCK);
 				int alt_m = (alt_v >= 0) ? open(alt_media, O_RDWR | O_NONBLOCK) : -1;
 				if (alt_v >= 0 && alt_m >= 0) {
+					/* Dispatch into the matching per-driver slot.
+					 * iter38 only had rkvdec/hantro pairs; iter40 +
+					 * LIBVA-1 extended this to rpi-hevc-dec and
+					 * daedalus_v4l2 for the Pi 5 mixed-decoder
+					 * deployment. */
 					if (strcmp(alt_driver, "rkvdec") == 0) {
 						driver_data->video_fd_rkvdec = alt_v;
 						driver_data->media_fd_rkvdec = alt_m;
-					} else {
+					} else if (strcmp(alt_driver, "hantro-vpu") == 0) {
 						driver_data->video_fd_hantro = alt_v;
 						driver_data->media_fd_hantro = alt_m;
+					} else if (strcmp(alt_driver, "rpi-hevc-dec") == 0) {
+						driver_data->video_fd_rpi_hevc_dec = alt_v;
+						driver_data->media_fd_rpi_hevc_dec = alt_m;
+#ifdef HAVE_DAEDALUS_V4L2
+					} else if (strcmp(alt_driver, "daedalus_v4l2") == 0) {
+						driver_data->video_fd_daedalus = alt_v;
+						driver_data->media_fd_daedalus = alt_m;
+#endif
+					} else {
+						/* Shouldn't happen — primary_driver branches
+						 * above only set alt_driver to one of the
+						 * names handled here.  Close and move on. */
+						close(alt_v);
+						close(alt_m);
+						alt_v = -1;
+						alt_m = -1;
+					}
+					if (alt_v >= 0) {
+						request_log("iter38: also opened %s decoder at %s + %s\n",
+							    alt_driver, alt_video, alt_media);
 					}
-					request_log("iter38: also opened %s decoder at %s + %s\n",
-						    alt_driver, alt_video, alt_media);
 				} else {
 					if (alt_v >= 0) close(alt_v);
 					if (alt_m >= 0) close(alt_m);
@@ -890,6 +962,12 @@ VAStatus RequestTerminate(VADriverContextP context)
 		close(driver_data->video_fd_vpu981);
 	if (driver_data->media_fd_vpu981 >= 0)
 		close(driver_data->media_fd_vpu981);
+#ifdef HAVE_DAEDALUS_V4L2
+	if (driver_data->video_fd_daedalus >= 0)
+		close(driver_data->video_fd_daedalus);
+	if (driver_data->media_fd_daedalus >= 0)
+		close(driver_data->media_fd_daedalus);
+#endif
 	/* Fall back to direct close if neither alt fd captured the active
 	 * pair (env-override path). */
 	if (driver_data->video_fd_rkvdec < 0 && driver_data->video_fd_hantro < 0) {