1 files changed, 124 insertions, 62 deletions

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 951e19231da2..4fc167b42cf0 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -97,13 +97,10 @@ struct rkvdec_h264_priv_tbl {
 	u8 err_info[RKV_ERROR_INFO_SIZE];
 };
 
-#define RKVDEC_H264_DPB_SIZE 16
-
 struct rkvdec_h264_reflists {
-	u8 p[RKVDEC_H264_DPB_SIZE];
-	u8 b0[RKVDEC_H264_DPB_SIZE];
-	u8 b1[RKVDEC_H264_DPB_SIZE];
-	u8 num_valid;
+	struct v4l2_h264_reference p[V4L2_H264_REF_LIST_LEN];
+	struct v4l2_h264_reference b0[V4L2_H264_REF_LIST_LEN];
+	struct v4l2_h264_reference b1[V4L2_H264_REF_LIST_LEN];
 };
 
 struct rkvdec_h264_run {
@@ -112,6 +109,7 @@ struct rkvdec_h264_run {
 	const struct v4l2_ctrl_h264_sps *sps;
 	const struct v4l2_ctrl_h264_pps *pps;
 	const struct v4l2_ctrl_h264_scaling_matrix *scaling_matrix;
+	struct vb2_buffer *ref_buf[V4L2_H264_NUM_DPB_ENTRIES];
 };
 
 struct rkvdec_h264_ctx {
@@ -661,8 +659,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 	WRITE_PPS(0xff, PROFILE_IDC);
 	WRITE_PPS(1, CONSTRAINT_SET3_FLAG);
 	WRITE_PPS(sps->chroma_format_idc, CHROMA_FORMAT_IDC);
-	WRITE_PPS(sps->bit_depth_luma_minus8 + 8, BIT_DEPTH_LUMA);
-	WRITE_PPS(sps->bit_depth_chroma_minus8 + 8, BIT_DEPTH_CHROMA);
+	WRITE_PPS(sps->bit_depth_luma_minus8, BIT_DEPTH_LUMA);
+	WRITE_PPS(sps->bit_depth_chroma_minus8, BIT_DEPTH_CHROMA);
 	WRITE_PPS(0, QPPRIME_Y_ZERO_TRANSFORM_BYPASS_FLAG);
 	WRITE_PPS(sps->log2_max_frame_num_minus4, LOG2_MAX_FRAME_NUM_MINUS4);
 	WRITE_PPS(sps->max_num_ref_frames, MAX_NUM_REF_FRAMES);
@@ -671,8 +669,17 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 		  LOG2_MAX_PIC_ORDER_CNT_LSB_MINUS4);
 	WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_DELTA_PIC_ORDER_ALWAYS_ZERO),
 		  DELTA_PIC_ORDER_ALWAYS_ZERO_FLAG);
-	WRITE_PPS(DIV_ROUND_UP(ctx->coded_fmt.fmt.pix_mp.width, 16), PIC_WIDTH_IN_MBS);
-	WRITE_PPS(DIV_ROUND_UP(ctx->coded_fmt.fmt.pix_mp.height, 16), PIC_HEIGHT_IN_MBS);
+
+	/*
+	 * Use the SPS values since they are already in macroblocks
+	 * dimensions, height can be field height (halved) if
+	 * V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY is not set and also it allows
+	 * decoding smaller images into larger allocation which can be used
+	 * to implementing SVC spatial layer support.
+	 */
+	WRITE_PPS(sps->pic_width_in_mbs_minus1 + 1, PIC_WIDTH_IN_MBS);
+	WRITE_PPS(sps->pic_height_in_map_units_minus1 + 1, PIC_HEIGHT_IN_MBS);
+
 	WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY),
 		  FRAME_MBS_ONLY_FLAG);
 	WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD),
@@ -725,15 +732,37 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 	}
 }
 
+static void lookup_ref_buf_idx(struct rkvdec_ctx *ctx,
+			       struct rkvdec_h264_run *run)
+{
+	const struct v4l2_ctrl_h264_decode_params *dec_params = run->decode_params;
+	u32 i;
+
+	for (i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) {
+		struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
+		const struct v4l2_h264_dpb_entry *dpb = run->decode_params->dpb;
+		struct vb2_queue *cap_q = &m2m_ctx->cap_q_ctx.q;
+		struct vb2_buffer *buf = NULL;
+
+		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) {
+			buf = vb2_find_buffer(cap_q, dpb[i].reference_ts);
+			if (!buf)
+				pr_debug("No buffer for reference_ts %llu",
+					 dpb[i].reference_ts);
+		}
+
+		run->ref_buf[i] = buf;
+	}
+}
+
 static void assemble_hw_rps(struct rkvdec_ctx *ctx,
+			    struct v4l2_h264_reflist_builder *builder,
 			    struct rkvdec_h264_run *run)
 {
 	const struct v4l2_ctrl_h264_decode_params *dec_params = run->decode_params;
 	const struct v4l2_h264_dpb_entry *dpb = dec_params->dpb;
 	struct rkvdec_h264_ctx *h264_ctx = ctx->priv;
-	const struct v4l2_ctrl_h264_sps *sps = run->sps;
 	struct rkvdec_h264_priv_tbl *priv_tbl = h264_ctx->priv_tbl.cpu;
-	u32 max_frame_num = 1 << (sps->log2_max_frame_num_minus4 + 4);
 
 	u32 *hw_rps = priv_tbl->rps;
 	u32 i, j;
@@ -751,39 +780,36 @@ static void assemble_hw_rps(struct rkvdec_ctx *ctx,
 		if (!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE))
 			continue;
 
-		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM ||
-		    dpb[i].frame_num < dec_params->frame_num) {
-			p[i] = dpb[i].frame_num;
-			continue;
-		}
-
-		p[i] = dpb[i].frame_num - max_frame_num;
+		p[i] = builder->refs[i].frame_num;
 	}
 
 	for (j = 0; j < RKVDEC_NUM_REFLIST; j++) {
-		for (i = 0; i < h264_ctx->reflists.num_valid; i++) {
-			u8 dpb_valid = 0;
-			u8 idx = 0;
+		for (i = 0; i < builder->num_valid; i++) {
+			struct v4l2_h264_reference *ref;
+			bool dpb_valid;
+			bool bottom;
 
 			switch (j) {
 			case 0:
-				idx = h264_ctx->reflists.p[i];
+				ref = &h264_ctx->reflists.p[i];
 				break;
 			case 1:
-				idx = h264_ctx->reflists.b0[i];
+				ref = &h264_ctx->reflists.b0[i];
 				break;
 			case 2:
-				idx = h264_ctx->reflists.b1[i];
+				ref = &h264_ctx->reflists.b1[i];
 				break;
 			}
 
-			if (idx >= ARRAY_SIZE(dec_params->dpb))
+			if (WARN_ON(ref->index >= ARRAY_SIZE(dec_params->dpb)))
 				continue;
-			dpb_valid = !!(dpb[idx].flags &
-				       V4L2_H264_DPB_ENTRY_FLAG_ACTIVE);
+
+			dpb_valid = run->ref_buf[ref->index] != NULL;
+			bottom = ref->fields == V4L2_H264_BOTTOM_FIELD_REF;
 
 			set_ps_field(hw_rps, DPB_INFO(i, j),
-				     idx | dpb_valid << 4);
+				     ref->index | dpb_valid << 4);
+			set_ps_field(hw_rps, BOTTOM_FLAG(i, j), bottom);
 		}
 	}
 }
@@ -854,29 +880,6 @@ static const u32 poc_reg_tbl_bottom_field[16] = {
 	RKVDEC_REG_H264_POC_REFER2(1)
 };
 
-static struct vb2_buffer *
-get_ref_buf(struct rkvdec_ctx *ctx, struct rkvdec_h264_run *run,
-	    unsigned int dpb_idx)
-{
-	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
-	const struct v4l2_h264_dpb_entry *dpb = run->decode_params->dpb;
-	struct vb2_queue *cap_q = &m2m_ctx->cap_q_ctx.q;
-	int buf_idx = -1;
-
-	if (dpb[dpb_idx].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)
-		buf_idx = vb2_find_timestamp(cap_q,
-					     dpb[dpb_idx].reference_ts, 0);
-
-	/*
-	 * If a DPB entry is unused or invalid, address of current destination
-	 * buffer is returned.
-	 */
-	if (buf_idx < 0)
-		return &run->base.bufs.dst->vb2_buf;
-
-	return vb2_get_buffer(cap_q, buf_idx);
-}
-
 static void config_registers(struct rkvdec_ctx *ctx,
 			     struct rkvdec_h264_run *run)
 {
@@ -949,8 +952,14 @@ static void config_registers(struct rkvdec_ctx *ctx,
 
 	/* config ref pic address & poc */
 	for (i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) {
-		struct vb2_buffer *vb_buf = get_ref_buf(ctx, run, i);
-
+		struct vb2_buffer *vb_buf = run->ref_buf[i];
+
+		/*
+		 * If a DPB entry is unused or invalid, address of current destination
+		 * buffer is returned.
+		 */
+		if (!vb_buf)
+			vb_buf = &dst_buf->vb2_buf;
 		refer_addr = vb2_dma_contig_plane_dma_addr(vb_buf, 0);
 
 		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)
@@ -976,10 +985,6 @@ static void config_registers(struct rkvdec_ctx *ctx,
 				       rkvdec->regs + RKVDEC_REG_H264_BASE_REFER15);
 	}
 
-	/*
-	 * Since support frame mode only
-	 * top_field_order_cnt is the same as bottom_field_order_cnt
-	 */
 	reg = RKVDEC_CUR_POC(dec_params->top_field_order_cnt);
 	writel_relaxed(reg, rkvdec->regs + RKVDEC_REG_CUR_POC0);
 
@@ -1021,13 +1026,61 @@ static int rkvdec_h264_adjust_fmt(struct rkvdec_ctx *ctx,
 	return 0;
 }
 
+static int rkvdec_h264_validate_sps(struct rkvdec_ctx *ctx,
+				    const struct v4l2_ctrl_h264_sps *sps)
+{
+	unsigned int width, height;
+
+	/*
+	 * TODO: The hardware supports 10-bit and 4:2:2 profiles,
+	 * but it's currently broken in the driver.
+	 * Reject them for now, until it's fixed.
+	 */
+	if (sps->chroma_format_idc > 1)
+		/* Only 4:0:0 and 4:2:0 are supported */
+		return -EINVAL;
+	if (sps->bit_depth_luma_minus8 != sps->bit_depth_chroma_minus8)
+		/* Luma and chroma bit depth mismatch */
+		return -EINVAL;
+	if (sps->bit_depth_luma_minus8 != 0)
+		/* Only 8-bit is supported */
+		return -EINVAL;
+
+	width = (sps->pic_width_in_mbs_minus1 + 1) * 16;
+	height = (sps->pic_height_in_map_units_minus1 + 1) * 16;
+
+	/*
+	 * When frame_mbs_only_flag is not set, this is field height,
+	 * which is half the final height (see (7-18) in the
+	 * specification)
+	 */
+	if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY))
+		height *= 2;
+
+	if (width > ctx->coded_fmt.fmt.pix_mp.width ||
+	    height > ctx->coded_fmt.fmt.pix_mp.height)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int rkvdec_h264_start(struct rkvdec_ctx *ctx)
 {
 	struct rkvdec_dev *rkvdec = ctx->dev;
 	struct rkvdec_h264_priv_tbl *priv_tbl;
 	struct rkvdec_h264_ctx *h264_ctx;
+	struct v4l2_ctrl *ctrl;
 	int ret;
 
+	ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl,
+			      V4L2_CID_STATELESS_H264_SPS);
+	if (!ctrl)
+		return -EINVAL;
+
+	ret = rkvdec_h264_validate_sps(ctx, ctrl->p_new.p_h264_sps);
+	if (ret)
+		return ret;
+
 	h264_ctx = kzalloc(sizeof(*h264_ctx), GFP_KERNEL);
 	if (!h264_ctx)
 		return -ENOMEM;
@@ -1095,22 +1148,22 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx)
 	/* Build the P/B{0,1} ref lists. */
 	v4l2_h264_init_reflist_builder(&reflist_builder, run.decode_params,
 				       run.sps, run.decode_params->dpb);
-	h264_ctx->reflists.num_valid = reflist_builder.num_valid;
 	v4l2_h264_build_p_ref_list(&reflist_builder, h264_ctx->reflists.p);
 	v4l2_h264_build_b_ref_lists(&reflist_builder, h264_ctx->reflists.b0,
 				    h264_ctx->reflists.b1);
 
 	assemble_hw_scaling_list(ctx, &run);
 	assemble_hw_pps(ctx, &run);
-	assemble_hw_rps(ctx, &run);
+	lookup_ref_buf_idx(ctx, &run);
+	assemble_hw_rps(ctx, &reflist_builder, &run);
 	config_registers(ctx, &run);
 
 	rkvdec_run_postamble(ctx, &run.base);
 
 	schedule_delayed_work(&rkvdec->watchdog_work, msecs_to_jiffies(2000));
 
-	writel(0xffffffff, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN);
-	writel(0xffffffff, rkvdec->regs + RKVDEC_REG_H264_ERR_E);
+	writel(0, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN);
+	writel(0, rkvdec->regs + RKVDEC_REG_H264_ERR_E);
 	writel(1, rkvdec->regs + RKVDEC_REG_PREF_LUMA_CACHE_COMMAND);
 	writel(1, rkvdec->regs + RKVDEC_REG_PREF_CHR_CACHE_COMMAND);
 
@@ -1122,9 +1175,18 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx)
 	return 0;
 }
 
+static int rkvdec_h264_try_ctrl(struct rkvdec_ctx *ctx, struct v4l2_ctrl *ctrl)
+{
+	if (ctrl->id == V4L2_CID_STATELESS_H264_SPS)
+		return rkvdec_h264_validate_sps(ctx, ctrl->p_new.p_h264_sps);
+
+	return 0;
+}
+
 const struct rkvdec_coded_fmt_ops rkvdec_h264_fmt_ops = {
 	.adjust_fmt = rkvdec_h264_adjust_fmt,
 	.start = rkvdec_h264_start,
 	.stop = rkvdec_h264_stop,
 	.run = rkvdec_h264_run,
+	.try_ctrl = rkvdec_h264_try_ctrl,
 };