media: hantro: Do not reorder H264 scaling list

Scaling list supplied from userspace should be in matrix order
and can be used without applying the inverse scanning process.

The HW also only support 8x8 scaling list for the Y component, indices 0
and 1 in the scaling list supplied from userspace.

Remove reordering and write the scaling matrix in an order expected by
the VPU, also only allocate memory for the two 8x8 lists supported.

Fixes: a9471e25629b ("media: hantro: Add core bits to support H264 decoding")
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>

diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c
index 02cbe7761769b6a5409257e599823ad5092b9612..694a330f508e72a826bcc93439c6127a6324347c 100644 (file)
--- a/drivers/staging/media/hantro/hantro_h264.c
+++ b/drivers/staging/media/hantro/hantro_h264.c
@@ -20,7 +20,7 @@
 /* Size with u32 units. */
 #define CABAC_INIT_BUFFER_SIZE         (460 * 2)
 #define POC_BUFFER_SIZE                        34
-#define SCALING_LIST_SIZE              (6 * 16 + 6 * 64)
+#define SCALING_LIST_SIZE              (6 * 16 + 2 * 64)
 
 #define HANTRO_CMP(a, b) ((a) < (b) ? -1 : 1)
 
@@ -194,23 +194,6 @@ static const u32 h264_cabac_table[] = {
        0x1f0c2517, 0x1f261440
 };
 
-/*
- * NOTE: The scaling lists are in zig-zag order, apply inverse scanning process
- * to get the values in matrix order. In addition, the hardware requires bytes
- * swapped within each subsequent 4 bytes. Both arrays below include both
- * transformations.
- */
-static const u32 zig_zag_4x4[] = {
-       3, 2, 7, 11, 6, 1, 0, 5, 10, 15, 14, 9, 4, 8, 13, 12
-};
-
-static const u32 zig_zag_8x8[] = {
-       3, 2, 11, 19, 10, 1, 0, 9, 18, 27, 35, 26, 17, 8, 7, 6,
-       15, 16, 25, 34, 43, 51, 42, 33, 24, 23, 14, 5, 4, 13, 22, 31,
-       32, 41, 50, 59, 58, 49, 40, 39, 30, 21, 12, 20, 29, 38, 47, 48,
-       57, 56, 55, 46, 37, 28, 36, 45, 54, 63, 62, 53, 44, 52, 61, 60
-};
-
 static void
 reorder_scaling_list(struct hantro_ctx *ctx)
 {
@@ -218,33 +201,23 @@ reorder_scaling_list(struct hantro_ctx *ctx)
        const struct v4l2_ctrl_h264_scaling_matrix *scaling = ctrls->scaling;
        const size_t num_list_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4);
        const size_t list_len_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4[0]);
-       const size_t num_list_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8);
        const size_t list_len_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8[0]);
        struct hantro_h264_dec_priv_tbl *tbl = ctx->h264_dec.priv.cpu;
-       u8 *dst = tbl->scaling_list;
-       const u8 *src;
+       u32 *dst = (u32 *)tbl->scaling_list;
+       const u32 *src;
        int i, j;
 
-       BUILD_BUG_ON(ARRAY_SIZE(zig_zag_4x4) != list_len_4x4);
-       BUILD_BUG_ON(ARRAY_SIZE(zig_zag_8x8) != list_len_8x8);
-       BUILD_BUG_ON(ARRAY_SIZE(tbl->scaling_list) !=
-                    num_list_4x4 * list_len_4x4 +
-                    num_list_8x8 * list_len_8x8);
-
-       src = &scaling->scaling_list_4x4[0][0];
-       for (i = 0; i < num_list_4x4; ++i) {
-               for (j = 0; j < list_len_4x4; ++j)
-                       dst[zig_zag_4x4[j]] = src[j];
-               src += list_len_4x4;
-               dst += list_len_4x4;
+       for (i = 0; i < num_list_4x4; i++) {
+               src = (u32 *)&scaling->scaling_list_4x4[i];
+               for (j = 0; j < list_len_4x4 / 4; j++)
+                       *dst++ = swab32(src[j]);
        }
 
-       src = &scaling->scaling_list_8x8[0][0];
-       for (i = 0; i < num_list_8x8; ++i) {
-               for (j = 0; j < list_len_8x8; ++j)
-                       dst[zig_zag_8x8[j]] = src[j];
-               src += list_len_8x8;
-               dst += list_len_8x8;
+       /* Only Intra/Inter Y lists */
+       for (i = 0; i < 2; i++) {
+               src = (u32 *)&scaling->scaling_list_8x8[i];
+               for (j = 0; j < list_len_8x8 / 4; j++)
+                       *dst++ = swab32(src[j]);
        }
 }