[Mesa-dev] [PATCH v2] st/va: Fix scaling list ordering for H.265

[Mark Thompson]

Mesa here requires the scaling lists in diagonal scan order, but
VAAPI passes them in raster scan order.  Therefore, rearrange the
elements when copying.

v2: Move scan tables to vl_zscan.c.
    Fix type in size assertion.

Signed-off-by: Mark Thompson <sw at jkqxz.net>
---
On 14/07/17 11:01, Christian König wrote:
> That just looks like the inversed Z-scan order we already have in vl_zscan.[hc].
> 
> Please use that one instead and/or add new defines into that file if necessary.

They are not the same as any of the existing orders, so I've added new tables.

Thanks,

- Mark


 src/gallium/auxiliary/vl/vl_zscan.c          | 21 ++++++++++++++++++
 src/gallium/auxiliary/vl/vl_zscan.h          |  2 ++
 src/gallium/state_trackers/va/picture_hevc.c | 33 ++++++++++++++++++++++------
 3 files changed, 49 insertions(+), 7 deletions(-)

diff --git a/src/gallium/auxiliary/vl/vl_zscan.c b/src/gallium/auxiliary/vl/vl_zscan.c
index 24d64525b7..75013c42bf 100644
--- a/src/gallium/auxiliary/vl/vl_zscan.c
+++ b/src/gallium/auxiliary/vl/vl_zscan.c
@@ -95,6 +95,27 @@ const int vl_zscan_alternate[] =
    38,46,54,62,39,47,55,63
 };
 
+const int vl_zscan_h265_up_right_diagonal_16[] =
+{
+   /* Up-right diagonal scan order for 4x4 blocks - see H.265 section 6.5.3. */
+    0,  4,  1,  8,  5,  2, 12,  9,
+    6,  3, 13, 10,  7, 14, 11, 15,
+};
+
+const int vl_zscan_h265_up_right_diagonal[] =
+{
+   /* Up-right diagonal scan order for 8x8 blocks - see H.265 section 6.5.3. */
+    0,  8,  1, 16,  9,  2, 24, 17,
+   10,  3, 32, 25, 18, 11,  4, 40,
+   33, 26, 19, 12,  5, 48, 41, 34,
+   27, 20, 13,  6, 56, 49, 42, 35,
+   28, 21, 14,  7, 57, 50, 43, 36,
+   29, 22, 15, 58, 51, 44, 37, 30,
+   23, 59, 52, 45, 38, 31, 60, 53,
+   46, 39, 61, 54, 47, 62, 55, 63,
+};
+
+
 static void *
 create_vert_shader(struct vl_zscan *zscan)
 {
diff --git a/src/gallium/auxiliary/vl/vl_zscan.h b/src/gallium/auxiliary/vl/vl_zscan.h
index 268cf0a6e3..292152e873 100644
--- a/src/gallium/auxiliary/vl/vl_zscan.h
+++ b/src/gallium/auxiliary/vl/vl_zscan.h
@@ -68,6 +68,8 @@ extern const int vl_zscan_normal_16[];
 extern const int vl_zscan_linear[];
 extern const int vl_zscan_normal[];
 extern const int vl_zscan_alternate[];
+extern const int vl_zscan_h265_up_right_diagonal_16[];
+extern const int vl_zscan_h265_up_right_diagonal[];
 
 struct pipe_sampler_view *
 vl_zscan_layout(struct pipe_context *pipe, const int layout[64], unsigned blocks_per_line);
diff --git a/src/gallium/state_trackers/va/picture_hevc.c b/src/gallium/state_trackers/va/picture_hevc.c
index 28743ee7aa..e879259ae1 100644
--- a/src/gallium/state_trackers/va/picture_hevc.c
+++ b/src/gallium/state_trackers/va/picture_hevc.c
@@ -25,6 +25,7 @@
  *
  **************************************************************************/
 
+#include "vl/vl_zscan.h"
 #include "va_private.h"
 
 void vlVaHandlePictureParameterBufferHEVC(vlVaDriver *drv, vlVaContext *context, vlVaBuffer *buf)
@@ -179,14 +180,32 @@ void vlVaHandlePictureParameterBufferHEVC(vlVaDriver *drv, vlVaContext *context,
 void vlVaHandleIQMatrixBufferHEVC(vlVaContext *context, vlVaBuffer *buf)
 {
    VAIQMatrixBufferHEVC *h265 = buf->data;
+   int i, j;
 
-   assert(buf->size >= sizeof(VAIQMatrixBufferH264) && buf->num_elements == 1);
-   memcpy(&context->desc.h265.pps->sps->ScalingList4x4, h265->ScalingList4x4, 6 * 16);
-   memcpy(&context->desc.h265.pps->sps->ScalingList8x8, h265->ScalingList8x8, 6 * 64);
-   memcpy(&context->desc.h265.pps->sps->ScalingList16x16, h265->ScalingList16x16, 6 * 64);
-   memcpy(&context->desc.h265.pps->sps->ScalingList32x32, h265->ScalingList32x32, 2 * 64);
-   memcpy(&context->desc.h265.pps->sps->ScalingListDCCoeff16x16, h265->ScalingListDC16x16, 6);
-   memcpy(&context->desc.h265.pps->sps->ScalingListDCCoeff32x32, h265->ScalingListDC32x32, 2);
+   assert(buf->size >= sizeof(VAIQMatrixBufferHEVC) && buf->num_elements == 1);
+
+   for (i = 0; i < 6; i++) {
+      for (j = 0; j < 16; j++)
+         context->desc.h265.pps->sps->ScalingList4x4[i][j] =
+                                h265->ScalingList4x4[i][vl_zscan_h265_up_right_diagonal_16[j]];
+
+      for (j = 0; j < 64; j++) {
+         context->desc.h265.pps->sps->ScalingList8x8[i][j] =
+                                h265->ScalingList8x8[i][vl_zscan_h265_up_right_diagonal[j]];
+         context->desc.h265.pps->sps->ScalingList16x16[i][j] =
+                                h265->ScalingList16x16[i][vl_zscan_h265_up_right_diagonal[j]];
+
+         if (i < 2)
+            context->desc.h265.pps->sps->ScalingList32x32[i][j] =
+                                   h265->ScalingList32x32[i][vl_zscan_h265_up_right_diagonal[j]];
+      }
+
+      context->desc.h265.pps->sps->ScalingListDCCoeff16x16[i] =
+                             h265->ScalingListDC16x16[i];
+      if (i < 2)
+         context->desc.h265.pps->sps->ScalingListDCCoeff32x32[i] =
+                                h265->ScalingListDC32x32[i];
+   }
 }
 
 void vlVaHandleSliceParameterBufferHEVC(vlVaContext *context, vlVaBuffer *buf)
-- 
2.11.0