media: hantro: Use post processor scaling capacities

Hantro G2 post processor is able to down scale decoded frames
by a factor of 2, 4 or 8.
Add enum_framesizes() ops to postproc_ops structure to enumerate the
possible output sizes for a given input resolution.
For G2 post-processor use fsize->index (from 0 to 3) as power of 2
divisor. As described in v4l2 documentation return -EINVAL when scaling
down isn't possible.

fluster scores:
77/147 for HEVC
143/303 for VP9
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@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.h

@@ -475,5 +475,7 @@ void hantro_postproc_disable(struct hantro_ctx *ctx);
 void hantro_postproc_enable(struct hantro_ctx *ctx);
 void hantro_postproc_free(struct hantro_ctx *ctx);
 int hantro_postproc_alloc(struct hantro_ctx *ctx);
+int hanto_postproc_enum_framesizes(struct hantro_ctx *ctx,
+				   struct v4l2_frmsizeenum *fsize);
 
 #endif /* HANTRO_H_ */

drivers/staging/media/hantro/hantro_g2_regs.h

@@ -290,6 +290,10 @@
 #define g2_buswidth		G2_DEC_REG(58, 8,  0x7)
 #define g2_max_burst		G2_DEC_REG(58, 0,  0xff)
 
+#define g2_down_scale_e		G2_DEC_REG(184, 7, 0x1)
+#define g2_down_scale_y		G2_DEC_REG(184, 2, 0x3)
+#define g2_down_scale_x		G2_DEC_REG(184, 0, 0x3)
+
 #define G2_REG_CONFIG				G2_SWREG(58)
 #define G2_REG_CONFIG_DEC_CLK_GATE_E		BIT(16)
 #define G2_REG_CONFIG_DEC_CLK_GATE_IDLE_E	BIT(17)
@@ -312,6 +316,8 @@
 #define G2_TILE_FILTER_ADDR		(G2_SWREG(179))
 #define G2_TILE_SAO_ADDR		(G2_SWREG(181))
 #define G2_TILE_BSD_ADDR		(G2_SWREG(183))
+#define G2_DS_DST			(G2_SWREG(186))
+#define G2_DS_DST_CHR			(G2_SWREG(188))
 
 #define g2_strm_buffer_len	G2_DEC_REG(258, 0, 0xffffffff)
 #define g2_strm_start_offset	G2_DEC_REG(259, 0, 0xffffffff)

drivers/staging/media/hantro/hantro_hw.h

@@ -247,10 +247,14 @@ struct hantro_postproc_ctx {
  *
  * @enable:		Enable the post-processor block. Optional.
  * @disable:		Disable the post-processor block. Optional.
+ * @enum_framesizes:	Enumerate possible scaled output formats.
+ *			Returns zero if OK, a negative value in error cases.
+ *			Optional.
  */
 struct hantro_postproc_ops {
 	void (*enable)(struct hantro_ctx *ctx);
 	void (*disable)(struct hantro_ctx *ctx);
+	int (*enum_framesizes)(struct hantro_ctx *ctx, struct v4l2_frmsizeenum *fsize);
 };
 
 /**

drivers/staging/media/hantro/hantro_postproc.c

@@ -100,21 +100,58 @@ static void hantro_postproc_g1_enable(struct hantro_ctx *ctx)
 	HANTRO_PP_REG_WRITE(vpu, display_width, ctx->dst_fmt.width);
 }
 
+static int down_scale_factor(struct hantro_ctx *ctx)
+{
+	if (ctx->src_fmt.width == ctx->dst_fmt.width)
+		return 0;
+
+	return DIV_ROUND_CLOSEST(ctx->src_fmt.width, ctx->dst_fmt.width);
+}
+
 static void hantro_postproc_g2_enable(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
 	struct vb2_v4l2_buffer *dst_buf;
 	size_t chroma_offset = ctx->dst_fmt.width * ctx->dst_fmt.height;
+	int down_scale = down_scale_factor(ctx);
 	dma_addr_t dst_dma;
 
 	dst_buf = hantro_get_dst_buf(ctx);
 	dst_dma = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
 
+	if (down_scale) {
+		hantro_reg_write(vpu, &g2_down_scale_e, 1);
+		hantro_reg_write(vpu, &g2_down_scale_y, down_scale >> 2);
+		hantro_reg_write(vpu, &g2_down_scale_x, down_scale >> 2);
+		hantro_write_addr(vpu, G2_DS_DST, dst_dma);
+		hantro_write_addr(vpu, G2_DS_DST_CHR, dst_dma + (chroma_offset >> down_scale));
+	} else {
 		hantro_write_addr(vpu, G2_RS_OUT_LUMA_ADDR, dst_dma);
 		hantro_write_addr(vpu, G2_RS_OUT_CHROMA_ADDR, dst_dma + chroma_offset);
+	}
 	hantro_reg_write(vpu, &g2_out_rs_e, 1);
 }
 
+static int hantro_postproc_g2_enum_framesizes(struct hantro_ctx *ctx,
+					      struct v4l2_frmsizeenum *fsize)
+{
+	/**
+	 * G2 scaler can scale down by 0, 2, 4 or 8
+	 * use fsize->index has power of 2 diviser
+	 **/
+	if (fsize->index > 3)
+		return -EINVAL;
+
+	if (!ctx->src_fmt.width || !ctx->src_fmt.height)
+		return -EINVAL;
+
+	fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
+	fsize->discrete.width = ctx->src_fmt.width >> fsize->index;
+	fsize->discrete.height = ctx->src_fmt.height >> fsize->index;
+
+	return 0;
+}
+
 void hantro_postproc_free(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
@@ -197,6 +234,17 @@ void hantro_postproc_enable(struct hantro_ctx *ctx)
 		vpu->variant->postproc_ops->enable(ctx);
 }
 
+int hanto_postproc_enum_framesizes(struct hantro_ctx *ctx,
+				   struct v4l2_frmsizeenum *fsize)
+{
+	struct hantro_dev *vpu = ctx->dev;
+
+	if (vpu->variant->postproc_ops && vpu->variant->postproc_ops->enum_framesizes)
+		return vpu->variant->postproc_ops->enum_framesizes(ctx, fsize);
+
+	return -EINVAL;
+}
+
 const struct hantro_postproc_ops hantro_g1_postproc_ops = {
 	.enable = hantro_postproc_g1_enable,
 	.disable = hantro_postproc_g1_disable,
@@ -205,4 +253,5 @@ const struct hantro_postproc_ops hantro_g1_postproc_ops = {
 const struct hantro_postproc_ops hantro_g2_postproc_ops = {
 	.enable = hantro_postproc_g2_enable,
 	.disable = hantro_postproc_g2_disable,
+	.enum_framesizes = hantro_postproc_g2_enum_framesizes,
 };

drivers/staging/media/hantro/hantro_v4l2.c

@@ -116,12 +116,6 @@ static int vidioc_enum_framesizes(struct file *file, void *priv,
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
 	const struct hantro_fmt *fmt;
 
-	if (fsize->index != 0) {
-		vpu_debug(0, "invalid frame size index (expected 0, got %d)\n",
-			  fsize->index);
-		return -EINVAL;
-	}
-
 	fmt = hantro_find_format(ctx, fsize->pixel_format);
 	if (!fmt) {
 		vpu_debug(0, "unsupported bitstream format (%08x)\n",
@@ -129,9 +123,14 @@ static int vidioc_enum_framesizes(struct file *file, void *priv,
 		return -EINVAL;
 	}
 
-	/* This only makes sense for coded formats */
-	if (fmt->codec_mode == HANTRO_MODE_NONE)
+	/* For non-coded formats check if postprocessing scaling is possible */
+	if (fmt->codec_mode == HANTRO_MODE_NONE && hantro_needs_postproc(ctx, fmt)) {
+		return hanto_postproc_enum_framesizes(ctx, fsize);
+	} else if (fsize->index != 0) {
+		vpu_debug(0, "invalid frame size index (expected 0, got %d)\n",
+			  fsize->index);
 		return -EINVAL;
+	}
 
 	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
 	fsize->stepwise = fmt->frmsize;