media: hantro: Fix H264 motion vector buffer offset

A decoded 8-bit 4:2:0 frame need memory for up to 448 bytes per
macroblock and is laid out in memory as follow:

+---------------------------+
| Y-plane   256 bytes x MBs |
+---------------------------+
| UV-plane  128 bytes x MBs |
+---------------------------+
| MV buffer  64 bytes x MBs |
+---------------------------+

The motion vector buffer offset is currently correct for 4:2:0 because
the extra space for motion vectors is overallocated with an extra
64 bytes x MBs.

Wrong offset for both destination and motion vector buffer are used
for the bottom field of field encoded content, wrong offset is
also used for 4:0:0 (monochrome) content.

Fix this by setting the motion vector address to the expected 384 bytes
x MBs offset for 4:2:0 and 256 bytes x MBs offset for 4:0:0 content.

Also use correct destination and motion vector buffer offset
for the bottom field of field encoded content.

While at it also extend the check for 4:0:0 (monochrome) to include an
additional check for High Profile (100).

Fixes: dea0a82f ("media: hantro: Add support for H264 decoding on G1")
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>

drivers/staging/media/hantro/hantro_g1_h264_dec.c

@@ -81,7 +81,7 @@ static void set_params(struct hantro_ctx *ctx)
 		reg |= G1_REG_DEC_CTRL4_CABAC_E;
 	if (sps->flags & V4L2_H264_SPS_FLAG_DIRECT_8X8_INFERENCE)
 		reg |= G1_REG_DEC_CTRL4_DIR_8X8_INFER_E;
-	if (sps->chroma_format_idc == 0)
+	if (sps->profile_idc >= 100 && sps->chroma_format_idc == 0)
 		reg |= G1_REG_DEC_CTRL4_BLACKWHITE_E;
 	if (pps->flags & V4L2_H264_PPS_FLAG_WEIGHTED_PRED)
 		reg |= G1_REG_DEC_CTRL4_WEIGHT_PRED_E;
@@ -234,6 +234,7 @@ static void set_buffers(struct hantro_ctx *ctx)
 	struct vb2_v4l2_buffer *src_buf, *dst_buf;
 	struct hantro_dev *vpu = ctx->dev;
 	dma_addr_t src_dma, dst_dma;
+	size_t offset = 0;
 
 	src_buf = hantro_get_src_buf(ctx);
 	dst_buf = hantro_get_dst_buf(ctx);
@@ -244,18 +245,30 @@ static void set_buffers(struct hantro_ctx *ctx)
 
 	/* Destination (decoded frame) buffer. */
 	dst_dma = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
-	vdpu_write_relaxed(vpu, dst_dma, G1_REG_ADDR_DST);
+	/* Adjust dma addr to start at second line for bottom field */
+	if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+		offset = ALIGN(ctx->src_fmt.width, MB_DIM);
+	vdpu_write_relaxed(vpu, dst_dma + offset, G1_REG_ADDR_DST);
 
 	/* Higher profiles require DMV buffer appended to reference frames. */
 	if (ctrls->sps->profile_idc > 66 && ctrls->decode->nal_ref_idc) {
-		size_t pic_size = ctx->h264_dec.pic_size;
-		size_t mv_offset = round_up(pic_size, 8);
+		unsigned int bytes_per_mb = 384;
 
-		if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
-			mv_offset += 32 * MB_WIDTH(ctx->dst_fmt.width);
+		/* DMV buffer for monochrome start directly after Y-plane */
+		if (ctrls->sps->profile_idc >= 100 &&
+		    ctrls->sps->chroma_format_idc == 0)
+			bytes_per_mb = 256;
+		offset = bytes_per_mb * MB_WIDTH(ctx->src_fmt.width) *
+			 MB_HEIGHT(ctx->src_fmt.height);
 
-		vdpu_write_relaxed(vpu, dst_dma + mv_offset,
-				   G1_REG_ADDR_DIR_MV);
+		/*
+		 * DMV buffer is split in two for field encoded frames,
+		 * adjust offset for bottom field
+		 */
+		if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+			offset += 32 * MB_WIDTH(ctx->src_fmt.width) *
+				  MB_HEIGHT(ctx->src_fmt.height);
+		vdpu_write_relaxed(vpu, dst_dma + offset, G1_REG_ADDR_DIR_MV);
 	}
 
 	/* Auxiliary buffer prepared in hantro_g1_h264_dec_prepare_table(). */