1 files changed, 104 insertions, 44 deletions

diff --git a/drivers/media/platform/verisilicon/hantro_postproc.c b/drivers/media/platform/verisilicon/hantro_postproc.c
index 6437423ccf3a..e94d1ba5ef10 100644
--- a/drivers/media/platform/verisilicon/hantro_postproc.c
+++ b/drivers/media/platform/verisilicon/hantro_postproc.c
@@ -21,11 +21,11 @@
 			 val); \
 }
 
-#define HANTRO_PP_REG_WRITE_S(vpu, reg_name, val) \
+#define HANTRO_PP_REG_WRITE_RELAXED(vpu, reg_name, val) \
 { \
-	hantro_reg_write_s(vpu, \
-			   &hantro_g1_postproc_regs.reg_name, \
-			   val); \
+	hantro_reg_write_relaxed(vpu, \
+				 &hantro_g1_postproc_regs.reg_name, \
+				 val); \
 }
 
 #define VPU_PP_IN_YUYV			0x0
@@ -49,7 +49,9 @@ static const struct hantro_postproc_regs hantro_g1_postproc_regs = {
 	.input_fmt = {G1_REG_PP_CONTROL, 29, 0x7},
 	.output_fmt = {G1_REG_PP_CONTROL, 26, 0x7},
 	.orig_width = {G1_REG_PP_MASK1_ORIG_WIDTH, 23, 0x1ff},
-	.display_width = {G1_REG_PP_DISPLAY_WIDTH, 0, 0xfff},
+	.display_width = {G1_REG_PP_DISPLAY_WIDTH_IN_EXT, 0, 0xfff},
+	.input_width_ext = {G1_REG_PP_DISPLAY_WIDTH_IN_EXT, 26, 0x7},
+	.input_height_ext = {G1_REG_PP_DISPLAY_WIDTH_IN_EXT, 29, 0x7},
 };
 
 bool hantro_needs_postproc(const struct hantro_ctx *ctx,
@@ -57,6 +59,10 @@ bool hantro_needs_postproc(const struct hantro_ctx *ctx,
 {
 	if (ctx->is_encoder)
 		return false;
+
+	if (ctx->need_postproc)
+		return true;
+
 	return fmt->postprocessed;
 }
 
@@ -68,7 +74,7 @@ static void hantro_postproc_g1_enable(struct hantro_ctx *ctx)
 	dma_addr_t dst_dma;
 
 	/* Turn on pipeline mode. Must be done first. */
-	HANTRO_PP_REG_WRITE_S(vpu, pipeline_en, 0x1);
+	HANTRO_PP_REG_WRITE(vpu, pipeline_en, 0x1);
 
 	src_pp_fmt = VPU_PP_IN_NV12;
 
@@ -99,11 +105,13 @@ static void hantro_postproc_g1_enable(struct hantro_ctx *ctx)
 	HANTRO_PP_REG_WRITE(vpu, output_height, ctx->dst_fmt.height);
 	HANTRO_PP_REG_WRITE(vpu, orig_width, MB_WIDTH(ctx->dst_fmt.width));
 	HANTRO_PP_REG_WRITE(vpu, display_width, ctx->dst_fmt.width);
+	HANTRO_PP_REG_WRITE(vpu, input_width_ext, MB_WIDTH(ctx->dst_fmt.width) >> 9);
+	HANTRO_PP_REG_WRITE(vpu, input_height_ext, MB_HEIGHT(ctx->dst_fmt.height >> 8));
 }
 
 static int down_scale_factor(struct hantro_ctx *ctx)
 {
-	if (ctx->src_fmt.width == ctx->dst_fmt.width)
+	if (ctx->src_fmt.width <= ctx->dst_fmt.width)
 		return 0;
 
 	return DIV_ROUND_CLOSEST(ctx->src_fmt.width, ctx->dst_fmt.width);
@@ -173,9 +181,11 @@ static int hantro_postproc_g2_enum_framesizes(struct hantro_ctx *ctx,
 void hantro_postproc_free(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
+	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
+	struct vb2_queue *queue = &m2m_ctx->cap_q_ctx.q;
 	unsigned int i;
 
-	for (i = 0; i < VB2_MAX_FRAME; ++i) {
+	for (i = 0; i < queue->max_num_buffers; ++i) {
 		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
 
 		if (priv->cpu) {
@@ -186,56 +196,106 @@ void hantro_postproc_free(struct hantro_ctx *ctx)
 	}
 }
 
-int hantro_postproc_alloc(struct hantro_ctx *ctx)
+static unsigned int hantro_postproc_buffer_size(struct hantro_ctx *ctx)
 {
-	struct hantro_dev *vpu = ctx->dev;
-	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
-	struct vb2_queue *cap_queue = &m2m_ctx->cap_q_ctx.q;
-	unsigned int num_buffers = cap_queue->num_buffers;
-	struct v4l2_pix_format_mplane pix_mp;
-	const struct hantro_fmt *fmt;
-	unsigned int i, buf_size;
-
-	/* this should always pick native format */
-	fmt = hantro_get_default_fmt(ctx, false, ctx->bit_depth);
-	if (!fmt)
-		return -EINVAL;
-	v4l2_fill_pixfmt_mp(&pix_mp, fmt->fourcc, ctx->src_fmt.width,
-			    ctx->src_fmt.height);
+	unsigned int buf_size;
 
-	buf_size = pix_mp.plane_fmt[0].sizeimage;
+	buf_size = ctx->ref_fmt.plane_fmt[0].sizeimage;
 	if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE)
-		buf_size += hantro_h264_mv_size(pix_mp.width,
-						pix_mp.height);
+		buf_size += hantro_h264_mv_size(ctx->ref_fmt.width,
+						ctx->ref_fmt.height);
 	else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_VP9_FRAME)
-		buf_size += hantro_vp9_mv_size(pix_mp.width,
-					       pix_mp.height);
-	else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_HEVC_SLICE)
-		buf_size += hantro_hevc_mv_size(pix_mp.width,
-						pix_mp.height);
+		buf_size += hantro_vp9_mv_size(ctx->ref_fmt.width,
+					       ctx->ref_fmt.height);
+	else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_HEVC_SLICE) {
+		buf_size += hantro_hevc_mv_size(ctx->ref_fmt.width,
+						ctx->ref_fmt.height);
+		if (ctx->hevc_dec.use_compression)
+			buf_size += hantro_hevc_compressed_size(ctx->ref_fmt.width,
+								ctx->ref_fmt.height);
+	}
+	else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_AV1_FRAME)
+		buf_size += hantro_av1_mv_size(ctx->ref_fmt.width,
+					       ctx->ref_fmt.height);
 
-	for (i = 0; i < num_buffers; ++i) {
-		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
+	return buf_size;
+}
+
+static int hantro_postproc_alloc(struct hantro_ctx *ctx, int index)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct hantro_aux_buf *priv = &ctx->postproc.dec_q[index];
+	unsigned int buf_size = hantro_postproc_buffer_size(ctx);
+
+	if (!buf_size)
+		return -EINVAL;
+
+	/*
+	 * The buffers on this queue are meant as intermediate
+	 * buffers for the decoder, so no mapping is needed.
+	 */
+	priv->attrs = DMA_ATTR_NO_KERNEL_MAPPING;
+	priv->cpu = dma_alloc_attrs(vpu->dev, buf_size, &priv->dma,
+				    GFP_KERNEL, priv->attrs);
+	if (!priv->cpu)
+		return -ENOMEM;
+	priv->size = buf_size;
+
+	return 0;
+}
 
-		/*
-		 * The buffers on this queue are meant as intermediate
-		 * buffers for the decoder, so no mapping is needed.
-		 */
-		priv->attrs = DMA_ATTR_NO_KERNEL_MAPPING;
-		priv->cpu = dma_alloc_attrs(vpu->dev, buf_size, &priv->dma,
-					    GFP_KERNEL, priv->attrs);
-		if (!priv->cpu)
-			return -ENOMEM;
-		priv->size = buf_size;
+int hantro_postproc_init(struct hantro_ctx *ctx)
+{
+	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
+	struct vb2_queue *cap_queue = &m2m_ctx->cap_q_ctx.q;
+	unsigned int num_buffers = vb2_get_num_buffers(cap_queue);
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < num_buffers; i++) {
+		ret = hantro_postproc_alloc(ctx, i);
+		if (ret) {
+			hantro_postproc_free(ctx);
+			return ret;
+		}
 	}
+
 	return 0;
 }
 
+dma_addr_t
+hantro_postproc_get_dec_buf_addr(struct hantro_ctx *ctx, int index)
+{
+	struct hantro_aux_buf *priv = &ctx->postproc.dec_q[index];
+	unsigned int buf_size = hantro_postproc_buffer_size(ctx);
+	struct hantro_dev *vpu = ctx->dev;
+	int ret;
+
+	if (priv->size < buf_size && priv->cpu) {
+		/* buffer is too small, release it */
+		dma_free_attrs(vpu->dev, priv->size, priv->cpu,
+			       priv->dma, priv->attrs);
+		priv->cpu = NULL;
+	}
+
+	if (!priv->cpu) {
+		/* buffer not already allocated, try getting a new one */
+		ret = hantro_postproc_alloc(ctx, index);
+		if (ret)
+			return 0;
+	}
+
+	if (!priv->cpu)
+		return 0;
+
+	return priv->dma;
+}
+
 static void hantro_postproc_g1_disable(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
 
-	HANTRO_PP_REG_WRITE_S(vpu, pipeline_en, 0x0);
+	HANTRO_PP_REG_WRITE(vpu, pipeline_en, 0x0);
 }
 
 static void hantro_postproc_g2_disable(struct hantro_ctx *ctx)