The real multiplanar wedge: probe MPLANE in surface.c, add NV12 mplane

This is what was actually broken — and it's much smaller than the STUDY
guessed.

The library is in fact multiplanar-aware throughout the v4l2.c helpers
(v4l2_setup_format, v4l2_get_format, v4l2_query_buffer, v4l2_queue_buffer,
v4l2_dequeue_buffer all branch on v4l2_type_is_mplane). The whole
"context.c / picture.c are single-plane" hypothesis from STUDY.md was wrong —
they derive output_type and capture_type from
video_format->v4l2_mplane and pass them through.

The bug is upstream of all that: driver_data->video_format is set in
RequestCreateSurfaces only, and the probe there only tries
V4L2_BUF_TYPE_VIDEO_CAPTURE (single-plane). On hantro the single-plane
ENUM_FMT returns nothing, video_format stays NULL, and every subsequent
operation hits the `if (video_format == NULL) return OPERATION_FAILED`
guard at the top of context.c / buffer.c / image.c. That's exactly what
Brave's vaCreateContext failure was — not a downstream multiplanar fault,
just the format-detection short-circuit firing.

Three small changes:

- src/video.c: add an NV12 multi-plane entry next to the existing
  single-plane NV12 / Sunxi entries. Same pixelformat fourcc (S264 vs NV12
  has nothing to do with mplane), distinguished by the v4l2_mplane bit.
- src/video.h + src/video.c: video_format_find() takes a `bool mplane`
  parameter and matches both fields. Without this the single-plane and
  multi-plane NV12 entries collide on pixelformat.
- src/surface.c: the probe block now tries V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE
  as a fallback after the single-plane probes return nothing. On a
  single-plane decoder the mplane probe is a no-op; on hantro it picks
  the new mplane NV12 entry, video_format gets set, and the rest of the
  library — already mplane-aware — does the right thing for OUTPUT
  S_FMT, REQBUFS, EXPBUF, QBUF, DQBUF.

Also: src/context.c: the H264 case still referenced V4L2_PIX_FMT_H264_SLICE_RAW
that we renamed in commit c1f5108. Caught now.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/context.c

@@ -104,7 +104,7 @@ VAStatus RequestCreateContext(VADriverContextP context, VAConfigID config_id,
 	case VAProfileH264ConstrainedBaseline:
 	case VAProfileH264MultiviewHigh:
 	case VAProfileH264StereoHigh:
-		pixelformat = V4L2_PIX_FMT_H264_SLICE_RAW;
+		pixelformat = V4L2_PIX_FMT_H264_SLICE;
 		break;
 
 	case VAProfileHEVCMain:

src/surface.c

@@ -73,17 +73,29 @@ VAStatus RequestCreateSurfaces2(VADriverContextP context, unsigned int format,
 
 
         if (!driver_data->video_format) {
+		/* Single-plane CAPTURE first (the original sunxi-cedrus path) */
 		found = v4l2_find_format(driver_data->video_fd,
 					 V4L2_BUF_TYPE_VIDEO_CAPTURE,
 					 V4L2_PIX_FMT_SUNXI_TILED_NV12);
 		if (found)
-			video_format = video_format_find(V4L2_PIX_FMT_SUNXI_TILED_NV12);
+			video_format = video_format_find(V4L2_PIX_FMT_SUNXI_TILED_NV12, false);
 
-		found = v4l2_find_format(driver_data->video_fd,
-					 V4L2_BUF_TYPE_VIDEO_CAPTURE,
-					 V4L2_PIX_FMT_NV12);
-		if (found)
-			video_format = video_format_find(V4L2_PIX_FMT_NV12);
+		if (video_format == NULL) {
+			found = v4l2_find_format(driver_data->video_fd,
+						 V4L2_BUF_TYPE_VIDEO_CAPTURE,
+						 V4L2_PIX_FMT_NV12);
+			if (found)
+				video_format = video_format_find(V4L2_PIX_FMT_NV12, false);
+		}
+
+		/* Multi-plane CAPTURE fallback (Rockchip hantro / RK3588 VDPU381) */
+		if (video_format == NULL) {
+			found = v4l2_find_format(driver_data->video_fd,
+						 V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
+						 V4L2_PIX_FMT_NV12);
+			if (found)
+				video_format = video_format_find(V4L2_PIX_FMT_NV12, true);
+		}
 
 		if (video_format == NULL)
 			return VA_STATUS_ERROR_OPERATION_FAILED;

src/video.c

@@ -45,6 +45,16 @@ static struct video_format formats[] = {
 		.planes_count		= 2,
 		.bpp			= 16,
 	},
+	{
+		.description		= "NV12 YUV (multi-plane)",
+		.v4l2_format		= V4L2_PIX_FMT_NV12,
+		.v4l2_buffers_count	= 1,
+		.v4l2_mplane		= true,
+		.drm_format		= DRM_FORMAT_NV12,
+		.drm_modifier		= DRM_FORMAT_MOD_NONE,
+		.planes_count		= 2,
+		.bpp			= 16,
+	},
 	{
 		.description		= "Sunxi tiled NV12 YUV",
 		.v4l2_format		= V4L2_PIX_FMT_SUNXI_TILED_NV12,
@@ -59,12 +69,13 @@ static struct video_format formats[] = {
 
 static unsigned int formats_count = sizeof(formats) / sizeof(formats[0]);
 
-struct video_format *video_format_find(unsigned int pixelformat)
+struct video_format *video_format_find(unsigned int pixelformat, bool mplane)
 {
 	unsigned int i;
 
 	for (i = 0; i < formats_count; i++)
-		if (formats[i].v4l2_format == pixelformat)
+		if (formats[i].v4l2_format == pixelformat &&
+		    formats[i].v4l2_mplane == mplane)
 			return &formats[i];
 
 	return NULL;

src/video.h

@@ -38,7 +38,7 @@ struct video_format {
 	unsigned int bpp;
 };
 
-struct video_format *video_format_find(unsigned int pixelformat);
+struct video_format *video_format_find(unsigned int pixelformat, bool mplane);
 bool video_format_is_linear(struct video_format *format);
 
 #endif