iter40: Pi 5 HEVC chapter — backend integration lands, bit-exact pending

Phase 6 implementation. Backend builds clean on higgs (Debian 13
trixie, aarch64), vainfo lists VAProfileHEVCMain via rpi-hevc-dec,
multi-device probe finds /dev/video19 + /dev/media1, CreateContext
+ S_FMT + REQBUFS + STREAMON all succeed.

Phase 7 partial: infrastructure works, 10 frames flow through the
pipeline (correct byte counts produced — 13824000 for 1280x720 x 10
NV12 frames). But every DQBUF CAPTURE returns V4L2_BUF_FLAG_ERROR
so output content is wrong (libva sha != kdirect sha). The decode
itself is failing on the rpi-hevc-dec side despite all ctrl
submissions returning success.

Code changes:
- request.h: video_fd_rpi_hevc_dec / media_fd_rpi_hevc_dec slots +
  has_hevc_ext_sps_rps_rpi_hevc_dec flag (mirrors iter38 + iter2
  pair-of-flags pattern, naturally false on Pi).
- request.c: known_decoder_drivers gains rpi-hevc-dec; primary-driver
  probe gets an else-if branch setting the new fds (Phase 5 F3);
  request_switch_device_for_profile prefers 'p' for HEVC when
  rpi-hevc-dec present.
- context.c: per-fd want_pixfmt (NC12 on Pi), capture_pixelformat
  taken from video_format slot (not hardcoded NV12/NV15);
  synthetic-SPS pre-seed gated off for Pi (Phase 5 F6);
  destination_sizes uses nv12_col128_uv_plane_offset for NC12 SAND
  layout (Phase 5 F2);
  per-driver HEVC_START_CODE (NONE on Pi, ANNEX_B on RK);
  per-driver context_object->h264_start_code (skip prepend on Pi).
- video.c: NV12_COL128 video_format entry (8-bit SAND, single
  buffer, 2 planes, NV12 drm_format with MOD_NONE so detile branch
  fires rather than tiled_to_planar).
- nv12_col128.c/.h: detile primitive (Y + UV per-plane, kernel
  hevc_d_video.c bytesperline formula + ffmpeg/Kynesim per-pixel
  offset). UV plane offset = 128 * ALIGN(h, 8) — within-column
  (SAND interleaves Y+UV per column, NOT plane-concatenated;
  earlier wrong formula caught by Phase 7 SEGV).
- image.c: #ifdef __arm__ extended to __arm__ || __aarch64__
  (Phase 5 F1 — guard was killing detile path on all aarch64
  hosts including fresnel iter39 NV15 path, masked because 10-bit
  never exercised); RequestCreateImage NC12 → NV12 stride override
  (linear width, not column-stride); copy_surface_to_image NC12
  detile branch (gates on fourcc + v4l2_format).
- nv15.h: fallback V4L2_PIX_FMT_NV15 define (Debian 13 headers
  omit it though they have NC12).
- nv12_col128.h: fallback V4L2_PIX_FMT_NV12_COL128 +
  V4L2_PIX_FMT_NV12_10_COL128 (Arch / mainline pre-Pi headers).
- tests/test_nv12_col128_detile.c: hand-crafted-bytes unit test;
  passes (8 cases: Y + UV for 4 widths incl. 1366 misaligned;
  UV-offset helper).
- meson.build / nv12_col128 sources listed.

Phase 7 status: not yet bit-exact. Remaining diagnosis: per-frame
S_EXT_CTRLS payload diff vs kdirect (kdirect sends 4 ctrls
SPS+PPS+decode_params+slice_array; ours sends 5 incl. scaling_matrix;
field ordering differs). Likely the slice_array contents need
per-driver handling for rpi-hevc-dec's expected layout. Beyond
in-session reach.

iter38 5/5 baseline on fresnel + ampere should be unaffected (new
fd stays -1 on non-Pi hosts; all gates either short-circuit on
fd-not-present or no-op).

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

src/request.c

@@ -93,6 +93,7 @@
 static const char * const known_decoder_drivers[] = {
 	"rkvdec",
 	"hantro-vpu",
+	"rpi-hevc-dec",  /* iter40: Pi 5 / CM5 stateless HEVC */
 	"cedrus",
 	"sun4i_csi",
 	NULL
@@ -431,12 +432,31 @@ int request_switch_device_for_profile(struct request_data *driver_data,
 	char kind = request_device_kind_for_profile(profile);
 	int target_video, target_media;
 
+	/*
+	 * iter40: HEVC override when rpi-hevc-dec is probed. The static
+	 * table (request_device_kind_for_profile) maps HEVC → 'r' (rkvdec)
+	 * because that's the canonical RK path. On Pi 5 there's no rkvdec
+	 * — rpi-hevc-dec is the only decoder. When BOTH would be present
+	 * (hypothetical mixed board), prefer rpi-hevc-dec for HEVC.
+	 *
+	 * Other rkvdec-routed profiles (VP9, H.264) stay on 'r' because
+	 * rpi-hevc-dec is HEVC-only.
+	 */
+	if ((profile == VAProfileHEVCMain || profile == VAProfileHEVCMain10) &&
+	    driver_data->video_fd_rpi_hevc_dec >= 0 &&
+	    driver_data->media_fd_rpi_hevc_dec >= 0) {
+		kind = 'p';
+	}
+
 	if (kind == 'r') {
 		target_video = driver_data->video_fd_rkvdec;
 		target_media = driver_data->media_fd_rkvdec;
 	} else if (kind == 'h') {
 		target_video = driver_data->video_fd_hantro;
 		target_media = driver_data->media_fd_hantro;
+	} else if (kind == 'p') {
+		target_video = driver_data->video_fd_rpi_hevc_dec;
+		target_media = driver_data->media_fd_rpi_hevc_dec;
 	} else {
 		return -1;
 	}
@@ -624,6 +644,8 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 	driver_data->media_fd_rkvdec = -1;
 	driver_data->video_fd_hantro = -1;
 	driver_data->media_fd_hantro = -1;
+	driver_data->video_fd_rpi_hevc_dec = -1;
+	driver_data->media_fd_rpi_hevc_dec = -1;
 
 	/*
 	 * iter38: probe BOTH rkvdec and hantro-vpu so a single libva session
@@ -654,6 +676,15 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 				alt_driver = "rkvdec";
 				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.
+				 * No alt driver to probe; the rkvdec / hantro slots
+				 * stay -1 and HEVC routes to 'p' via
+				 * request_device_kind_for_profile. */
+				primary_driver = "rpi-hevc-dec";
+				alt_driver = NULL;
+				driver_data->video_fd_rpi_hevc_dec = video_fd;
+				driver_data->media_fd_rpi_hevc_dec = media_fd;
 			}
 		}
 
@@ -693,11 +724,19 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 		probe_hevc_ext_sps_rps_controls(driver_data->video_fd_rkvdec);
 	driver_data->has_hevc_ext_sps_rps_hantro =
 		probe_hevc_ext_sps_rps_controls(driver_data->video_fd_hantro);
+	driver_data->has_hevc_ext_sps_rps_rpi_hevc_dec =
+		probe_hevc_ext_sps_rps_controls(driver_data->video_fd_rpi_hevc_dec);
 	if (driver_data->has_hevc_ext_sps_rps_rkvdec) {
 		request_log("iter2: kernel registers HEVC EXT_SPS_{ST,LT}_RPS "
 			    "controls on rkvdec fd (will route through "
 			    "vendored GStreamer parser)\n");
 	}
+	if (driver_data->video_fd_rpi_hevc_dec >= 0) {
+		request_log("iter40: also opened rpi-hevc-dec at video_fd=%d "
+			    "media_fd=%d (Pi 5 HEVC stateless)\n",
+			    driver_data->video_fd_rpi_hevc_dec,
+			    driver_data->media_fd_rpi_hevc_dec);
+	}
 
 	status = VA_STATUS_SUCCESS;
 	goto complete;