DEBUG: hex-dump OUTPUT and CAPTURE buffer contents per frame

Diagnostic-only patch (NOT for upstream). Hex-dumps:
  - First 32 bytes of OUTPUT buffer at QBUF time in
    picture.c::RequestEndPicture (i.e. what we feed the kernel)
  - First 32 bytes of CAPTURE Y-plane after DQBUF in
    surface.c::RequestSyncSurface (i.e. what kernel returned)

Lets us see whether:
  - OUTPUT bitstream begins with valid ANNEX_B start code + NAL
    header byte (e.g. `00 00 01 65` for IDR slice)
  - CAPTURE Y-plane after decode contains varied luma data
    (working) vs. all-zeros / repeating pattern (kernel didn't
    write anything).

Removed once Step 1 decode is verified working. Output goes via
existing request_log() to stderr.

Signed-off-by: Markus Fritsche <fritsche.markus@gmail.com>

src/picture.c

@@ -36,6 +36,7 @@
 #include "mpeg2.h"
 
 #include <assert.h>
+#include <stdio.h>
 #include <string.h>
 
 #include <errno.h>
@@ -354,6 +355,27 @@ VAStatus RequestEndPicture(VADriverContextP context, VAContextID context_id)
 	if (rc < 0)
 		return VA_STATUS_ERROR_OPERATION_FAILED;
 
+	/*
+	 * DEBUG INSTRUMENTATION (0010): hex-dump first 32 bytes of the
+	 * OUTPUT buffer at the moment we hand it to the kernel. Helps
+	 * pin down whether our bitstream prepend logic is correct.
+	 * For a valid ANNEX_B IDR slice the dump should start
+	 * 00 00 01 65 ... (00 00 01 = start code; 0x65 = nal_ref_idc=3,
+	 * nal_unit_type=5 = IDR slice). Removed once Step 1 decode is
+	 * verified working.
+	 */
+	{
+		const unsigned char *p = surface_object->source_data;
+		char hex[32 * 3 + 1] = { 0 };
+		unsigned int i, n = surface_object->slices_size < 32 ?
+				    surface_object->slices_size : 32;
+		for (i = 0; i < n; i++)
+			snprintf(hex + i * 3, 4, " %02x", p[i]);
+		request_log("OUTPUT[idx=%u, len=%u]:%s\n",
+			    surface_object->source_index,
+			    surface_object->slices_size, hex);
+	}
+
 	rc = v4l2_queue_buffer(driver_data->video_fd, request_fd, output_type,
 			       &surface_object->timestamp,
 			       surface_object->source_index,

src/surface.c

@@ -29,6 +29,7 @@
 
 #include <assert.h>
 #include <errno.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
@@ -364,6 +365,30 @@ VAStatus RequestSyncSurface(VADriverContextP context, VASurfaceID surface_id)
 		goto error;
 	}
 
+	/*
+	 * DEBUG INSTRUMENTATION (0010): hex-dump first 32 bytes of the
+	 * decoded CAPTURE Y-plane after DQBUF. If the kernel actually
+	 * decoded the frame, these should reflect a real Y-luma pattern
+	 * (varied bytes). All-zero or all-identical means no decode
+	 * landed pixels in the buffer. Removed once Step 1 is verified.
+	 */
+	{
+		const unsigned char *p =
+			(unsigned char *)surface_object->destination_map[0];
+		char hex[32 * 3 + 1] = { 0 };
+		unsigned int i;
+		if (p == NULL) {
+			request_log("CAPTURE[idx=%u, plane0]: (NULL)\n",
+				    surface_object->destination_index);
+		} else {
+			for (i = 0; i < 32; i++)
+				snprintf(hex + i * 3, 4, " %02x", p[i]);
+			request_log("CAPTURE[idx=%u, plane0]:%s\n",
+				    surface_object->destination_index,
+				    hex);
+		}
+	}
+
 	surface_object->status = VASurfaceDisplaying;
 
 	status = VA_STATUS_SUCCESS;