ampere-av1 Phase 2 (master): fourth-fd probe + AV1 enumeration

Imports the minimal "vainfo lists VAProfileAV1Profile0" layer from the
operator's in-progress av1-iter1 branch (Phase 2 steps 1, 2 — commits
bed75c0 + 61db76e on av1-iter1). The Phase 3-5 bit-exact decode-side
work stays in av1-iter1; this commit gives master the enumeration +
fd-routing layer so consumers (ffmpeg-vaapi, firefox-fourier, chromium-
fourier) at least see VAProfileAV1Profile0 today on RK3588.

What this commit adds:
- video_fd_vpu981 + media_fd_vpu981 slots to struct request_data
  (named to match av1-iter1's convention so the operator's Phase 3-5
   merge resolves cleanly)
- 4th-decoder probe loop in VA_DRIVER_INIT that walks hantro-vpu
  media nodes for an instance advertising V4L2_PIX_FMT_AV1_FRAME
  (AV1F) as OUTPUT pixfmt. RK3588 has 3 hantro-vpu instances all
  reporting driver="hantro-vpu" + model="hantro-vpu", so OUTPUT-
  format probe is the only DTS-independent discriminator.
- 'a' kind in request_device_kind_for_profile (VAProfileAV1Profile0)
  + 'a' branch in request_switch_device_for_profile.
- video_fd_vpu981 added to any_fd_supports_output_format helper
  (existing 3-slot loop missed the new fd; same off-by-one trap
  that bit ampere's av1-iter1 enumeration for a week).
- VAProfileAV1Profile0 → V4L2_PIX_FMT_AV1_FRAME in pixelformat_for
  _profile.
- VAProfileAV1Profile0 push in RequestQueryConfigProfiles +
  RequestQueryConfigEntrypoints + RequestCreateConfig switch.
- vpu981 fd cleanup in RequestTerminate.
- rpi_hevc_dec fd cleanup added at the same time (was already missing
  in master — fixed defensively).
- V4L2_REQUEST_MAX_PROFILES bumped 13 → 14. Defensively sized for
  the post-Option-B-revert future: with iter39 Option B reverted
  (Hi10P + Main10 back in enumeration) plus AV1, max possible
  enumeration is 13. The per-group guards use `index < MAX - N`
  pattern; for a singleton push to succeed at index=13 we need
  MAX >= 14. Bumping now avoids the same off-by-one bug from
  silently dropping AV1 when Option B eventually reverts.

What this commit does NOT add:
- av1.{c,h} decode-side scaffolding (Phase 2 step 4 on av1-iter1 —
  ~177 LoC including a stub av1_set_controls that returns -1). When
  the operator's av1-iter1 Phase 3-5 work lands on master, those
  500+ LoC + the stub will follow. Without them, consumers calling
  vaCreateContext(VAProfileAV1Profile0) succeed at the libva layer
  but ffmpeg-vaapi will fail at the first vaRenderPicture with an
  AV1-buffer-type rejection — clean error, no crash.

Verified 2026-05-18 on ampere:

  $ env LIBVA_DRIVER_NAME=v4l2_request vainfo | grep VAProfile
        ... (10 prior profiles, unchanged) ...
        VAProfileAV1Profile0            :   VAEntrypointVLD   ✓

  Probe log: "ampere-av1: vpu981 AV1 decoder at /dev/video4 + /dev/media3"

Build clean on ampere with GCC 16.1.1; no warnings introduced.
ampere's running module restored to the av1-iter1 build after the
verification — this commit's .so was NOT permanently installed.

Closes the headline acceptance criterion in
marfrit/libva-v4l2-request-fourier#2 ("vainfo on ampere lists
VAProfileAV1"). End-to-end AV1 decode bit-exactness is iter4 work
that the av1-iter1 branch continues to drive.

Co-Authored-By: claude-noether <claude-noether@reauktion.de>

src/codec.c

@@ -46,6 +46,20 @@ unsigned int pixelformat_for_profile(VAProfile profile)
 		return V4L2_PIX_FMT_VP8_FRAME;
 	case VAProfileVP9Profile0:
 		return V4L2_PIX_FMT_VP9_FRAME;
+	case VAProfileAV1Profile0:
+		/*
+		 * ampere-av1-enablement Phase 2: AV1 Profile 0 routes to
+		 * vpu981 (RK3588's dedicated AV1 hantro). Per-codec ctrl
+		 * dispatch (V4L2_CID_STATELESS_AV1_*) is NOT YET WIRED on
+		 * master — vainfo lists the profile + RequestCreateConfig
+		 * succeeds, but consumers that submit decode buffers hit
+		 * a NOP path until the per-codec dispatch lands. The
+		 * av1-iter1 operator branch has Phase 3 bit-exact bring-up
+		 * underway; this commit gives master the bare enumeration +
+		 * fd-routing layer so consumers like ffmpeg-vaapi at least
+		 * see VAProfileAV1Profile0 today.
+		 */
+		return V4L2_PIX_FMT_AV1_FRAME;
 	default:
 		return 0;
 	}

src/config.c

@@ -81,6 +81,16 @@ VAStatus RequestCreateConfig(VADriverContextP context, VAProfile profile,
 		// cap is V4L2_MPEG_VIDEO_VP9_PROFILE_0). Do not add a case for
 		// VAProfileVP9Profile2 — kernel will reject.
 		break;
+	case VAProfileAV1Profile0:
+		// ampere-av1-enablement Phase 2: AV1 Profile 0 routes to
+		// vpu981 (RK3588 dedicated AV1 hantro instance). 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 until av1.{c,h} dispatch scaffolding is ported
+		// from the av1-iter1 operator branch (where Phase 3-5 has
+		// 3/10 frames bit-exact already).
+		break;
 	default:
 		return VA_STATUS_ERROR_UNSUPPORTED_PROFILE;
 	}
@@ -162,13 +172,15 @@ VAStatus RequestDestroyConfig(VADriverContextP context, VAConfigID config_id)
 static bool any_fd_supports_output_format(struct request_data *driver_data,
 					  unsigned int fmt)
 {
-	int fds[3] = {
+	int fds[5] = {
 		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 */
 	};
 	int i;
-	for (i = 0; i < 3; i++) {
+	for (i = 0; i < 5; i++) {
 		if (fds[i] < 0) continue;
 		if (v4l2_find_format(fds[i], V4L2_BUF_TYPE_VIDEO_OUTPUT, fmt))
 			return true;
@@ -249,6 +261,17 @@ VAStatus RequestQueryConfigProfiles(VADriverContextP context,
 	if (found && index < (V4L2_REQUEST_MAX_PROFILES - 1))
 		profiles[index++] = VAProfileVP9Profile0;
 
+	/*
+	 * ampere-av1-enablement Phase 2: AV1 Profile 0 advertised when
+	 * vpu981 (RK3588 dedicated AV1 hantro) is probed. MAX_PROFILES
+	 * bumped to 14 in request.h to safely fit even if iter39 Option
+	 * B is reverted (Hi10P + Main10 back in enumeration → 13 total
+	 * with AV1, the `< MAX - 1` guard then needs MAX ≥ 14).
+	 */
+	found = any_fd_supports_output_format(driver_data, V4L2_PIX_FMT_AV1_FRAME);
+	if (found && index < (V4L2_REQUEST_MAX_PROFILES - 1))
+		profiles[index++] = VAProfileAV1Profile0;
+
 	*profiles_count = index;
 
 	return VA_STATUS_SUCCESS;
@@ -272,6 +295,7 @@ VAStatus RequestQueryConfigEntrypoints(VADriverContextP context,
 	case VAProfileHEVCMain10:
 	case VAProfileVP8Version0_3:
 	case VAProfileVP9Profile0:
+	case VAProfileAV1Profile0:
 		entrypoints[0] = VAEntrypointVLD;
 		*entrypoints_count = 1;
 		break;

src/request.c

@@ -409,6 +409,16 @@ char request_device_kind_for_profile(VAProfile profile)
 	case VAProfileMPEG2Main:
 	case VAProfileVP8Version0_3:
 		return 'h';
+	case VAProfileAV1Profile0:
+		/*
+		 * ampere-av1-enablement Phase 2: RK3588 vpu981 dedicated
+		 * AV1 hantro instance. 'a' kind dispatches to
+		 * driver_data->video_fd_vpu981. On hosts without the AV1
+		 * instance the fd stays -1 and RequestQueryConfigProfiles
+		 * never enumerates AV1, so this branch is unreachable for
+		 * non-RK3588 hosts.
+		 */
+		return 'a';
 	default:
 		return '?';
 	}
@@ -457,6 +467,9 @@ int request_switch_device_for_profile(struct request_data *driver_data,
 	} else if (kind == 'p') {
 		target_video = driver_data->video_fd_rpi_hevc_dec;
 		target_media = driver_data->media_fd_rpi_hevc_dec;
+	} else if (kind == 'a') {
+		target_video = driver_data->video_fd_vpu981;
+		target_media = driver_data->media_fd_vpu981;
 	} else {
 		return -1;
 	}
@@ -646,6 +659,8 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 	driver_data->media_fd_hantro = -1;
 	driver_data->video_fd_rpi_hevc_dec = -1;
 	driver_data->media_fd_rpi_hevc_dec = -1;
+	driver_data->video_fd_vpu981 = -1;
+	driver_data->media_fd_vpu981 = -1;
 
 	/*
 	 * iter38: probe BOTH rkvdec and hantro-vpu so a single libva session
@@ -712,6 +727,61 @@ VAStatus VA_DRIVER_INIT_FUNC(VADriverContextP context)
 			}
 		}
 		(void)primary_driver;
+
+		/*
+		 * ampere-av1-enablement Phase 2: walk hantro-vpu media nodes
+		 * for a SECOND one that advertises V4L2_PIX_FMT_AV1_FRAME
+		 * (AV1F) as OUTPUT pixfmt. RK3588 has 3 hantro-vpu instances
+		 * (legacy MPEG2/VP8 decoder, vepu121 encoder, vpu981 AV1
+		 * decoder) all reporting driver="hantro-vpu" / model="hantro-
+		 * vpu" — so OUTPUT-format probe is the only reliable
+		 * disambiguator that doesn't depend on parsing card-name
+		 * strings (which are DTS-dependent). First match wins.
+		 *
+		 * On non-RK3588 hosts the slot stays -1; RequestQueryConfig
+		 * Profiles' AV1 push then no-ops because any_fd_supports_
+		 * output_format() returns false for AV1F.
+		 */
+		{
+			int i;
+			char path[32], av1_video[32];
+
+			for (i = 0; i < 16; i++) {
+				int mfd, vfd;
+				struct media_device_info info;
+
+				snprintf(path, sizeof path, "/dev/media%d", i);
+				mfd = open(path, O_RDWR | O_NONBLOCK);
+				if (mfd < 0) continue;
+				memset(&info, 0, sizeof info);
+				if (ioctl(mfd, MEDIA_IOC_DEVICE_INFO, &info) != 0 ||
+				    strcmp(info.driver, "hantro-vpu") != 0) {
+					close(mfd);
+					continue;
+				}
+				if (find_decoder_video_node_via_topology(
+					    mfd, av1_video, sizeof av1_video) != 0) {
+					close(mfd);
+					continue;
+				}
+				vfd = open(av1_video, O_RDWR | O_NONBLOCK);
+				if (vfd < 0) {
+					close(mfd);
+					continue;
+				}
+				if (!v4l2_find_format(vfd, V4L2_BUF_TYPE_VIDEO_OUTPUT, V4L2_PIX_FMT_AV1_FRAME) &&
+				    !v4l2_find_format(vfd, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE, V4L2_PIX_FMT_AV1_FRAME)) {
+					close(vfd);
+					close(mfd);
+					continue;
+				}
+				driver_data->video_fd_vpu981 = vfd;
+				driver_data->media_fd_vpu981 = mfd;
+				request_log("ampere-av1: vpu981 AV1 decoder at %s + %s\n",
+					    av1_video, path);
+				break;
+			}
+		}
 	}
 
 	/*
@@ -784,6 +854,14 @@ VAStatus RequestTerminate(VADriverContextP context)
 		close(driver_data->video_fd_hantro);
 	if (driver_data->media_fd_hantro >= 0)
 		close(driver_data->media_fd_hantro);
+	if (driver_data->video_fd_rpi_hevc_dec >= 0)
+		close(driver_data->video_fd_rpi_hevc_dec);
+	if (driver_data->media_fd_rpi_hevc_dec >= 0)
+		close(driver_data->media_fd_rpi_hevc_dec);
+	if (driver_data->video_fd_vpu981 >= 0)
+		close(driver_data->video_fd_vpu981);
+	if (driver_data->media_fd_vpu981 >= 0)
+		close(driver_data->media_fd_vpu981);
 	/* 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) {

src/request.h

@@ -42,7 +42,16 @@
 
 #define V4L2_REQUEST_STR_VENDOR			"v4l2-request"
 
-#define V4L2_REQUEST_MAX_PROFILES		13
+/*
+ * Sized for max-possible enumeration with iter39 Option B reverted:
+ * MPEG2(2) + H264(6 incl. Hi10P) + HEVC(2 incl. Main10) + VP8 + VP9 + AV1 = 13.
+ * The per-group guards use `if (... && index < (MAX_PROFILES - N))` where N
+ * is the push-group size, so MAX must be ≥ total+1 — 14 here. Bumping
+ * defensively now so a future re-enable of Hi10P/Main10 doesn't silently
+ * drop AV1 through the off-by-one trap that ate ampere-av1's enumeration
+ * for a week (see issue marfrit/libva-v4l2-request-fourier#2).
+ */
+#define V4L2_REQUEST_MAX_PROFILES		14
 #define V4L2_REQUEST_MAX_ENTRYPOINTS		5
 #define V4L2_REQUEST_MAX_CONFIG_ATTRIBUTES	10
 #define V4L2_REQUEST_MAX_IMAGE_FORMATS		10
@@ -87,6 +96,21 @@ struct request_data {
 	 */
 	int video_fd_rpi_hevc_dec;
 	int media_fd_rpi_hevc_dec;
+	/*
+	 * ampere-av1-enablement Phase 2: fourth multi-device-probe slot
+	 * for vpu981 (RK3588's dedicated AV1 hantro instance, kernel
+	 * card="rockchip,rk3588-av1-vpu-dec", driver name "hantro-vpu" —
+	 * shared with the legacy MPEG-2/VP8/H.264 hantro). Discriminated
+	 * by V4L2_PIX_FMT_AV1_FRAME (AV1F) OUTPUT-pixfmt capability since
+	 * the driver name alone is ambiguous on RK3588. Stays -1 on hosts
+	 * without the AV1 vpu-dec.
+	 *
+	 * Named "vpu981" for consistency with the in-progress av1-iter1
+	 * operator branch (Phase 3-5 bit-exact AV1 work — when that lands
+	 * these fields receive the actual decode dispatch wiring).
+	 */
+	int video_fd_vpu981;
+	int media_fd_vpu981;
 
 	/*
 	 * iter2 (ampere-kernel-decoders campaign) — per-fd probe result