iter5 sweep: remove iter1 patch-0010 hex-dumps + patch-0011 sentinel

picture.c: remove the 0xab sentinel write into CAPTURE buffer first
32 bytes pre-QBUF + the OUTPUT hex-dump pre-QBUF. Both were iter1
diagnostics for "where does the buffer write go?" investigation.

surface.c: remove the post-DQBUF CAPTURE Y-plane hex-dump + luma
variance signal. The msync(MS_SYNC|MS_INVALIDATE) was added as a
companion fix for the cached-mmap issue surfaced by the dump itself —
removing the dump removes the need for the msync.

With iter1+iter2+iter3+iter4 fixes landed, these dumps fire on every
single frame and produce hundreds of MB of log noise during sustained
decode. Now gone.

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

src/picture.c

@@ -371,51 +371,12 @@ VAStatus RequestEndPicture(VADriverContextP context, VAContextID context_id)
 	if (rc != VA_STATUS_SUCCESS)
 		return rc;
 
-	/*
-	 * DEBUG INSTRUMENTATION (0011): write a sentinel pattern into
-	 * the CAPTURE buffer's first 32 bytes BEFORE QBUF. If after
-	 * DQBUF the sentinel survives (per surface.c hex dump), the
-	 * kernel never wrote to this buffer. If the sentinel is gone
-	 * (replaced by zeros), the kernel did write but our CPU read
-	 * sees stale-cached data — cache-coherency issue.
-	 */
-	{
-		unsigned char *p = (unsigned char *)
-			surface_object->destination_map[0];
-		if (p != NULL) {
-			unsigned int i;
-			for (i = 0; i < 32; i++)
-				p[i] = 0xab;
-		}
-	}
-
 	rc = v4l2_queue_buffer(driver_data->video_fd, -1, capture_type, NULL,
 			       surface_object->destination_index, 0,
 			       surface_object->destination_buffers_count);
 	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

@@ -509,48 +509,6 @@ VAStatus RequestSyncSurface(VADriverContextP context, VASurfaceID surface_id)
 		cap_pool_mark_decoded(&driver_data->capture_pool,
 				      surface_object->current_slot);
 
-	/*
-	 * DEBUG INSTRUMENTATION (0010): hex-dump first 32 bytes of the
-	 * decoded CAPTURE Y-plane after DQBUF, plus a 32-byte luma
-	 * variance signal (max - min) so we can tell at a glance whether
-	 * the bytes are real decoded pixels or a uniform fill.
-	 *
-	 * Cache hygiene fix (2026-05-04): without msync(MS_SYNC|
-	 * MS_INVALIDATE) the previous version of this dump consistently
-	 * showed the patch-0011 sentinel (0xab) even when the kernel had
-	 * DMA-overwritten the buffer with real pixels — userspace's
-	 * cached mmap line for the first 32 bytes contained the sentinel
-	 * write and was never invalidated by DQBUF alone on this hantro
-	 * CMA-backed config. Caused half a day of mistaken "kernel never
-	 * wrote the buffer" diagnosis (see libva-multiplanar campaign
-	 * phase0_evidence/2026-05-04-kernel-trace/findings.md). The
-	 * msync() forces the kernel to invalidate userspace cache for
-	 * this region so the read goes to physical memory.
-	 */
-	{
-		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 {
-			unsigned char ymin = 0xff, ymax = 0;
-			(void)msync(p, 32, MS_SYNC | MS_INVALIDATE);
-			for (i = 0; i < 32; i++) {
-				unsigned char y = p[i];
-				snprintf(hex + i * 3, 4, " %02x", y);
-				if (y < ymin) ymin = y;
-				if (y > ymax) ymax = y;
-			}
-			request_log("CAPTURE[idx=%u, plane0]:%s "
-				    "(ymin=0x%02x ymax=0x%02x var=%u)\n",
-				    surface_object->destination_index,
-				    hex, ymin, ymax,
-				    (unsigned)(ymax - ymin));
-		}
-	}
 
 	surface_object->status = VASurfaceDisplaying;