[PATCH RFC 03/12] media: rockchip: rkvenc: Prepare the VEPU580 helpers for a second codec

[Arun Iyengar via B4 Relay <devnull+aiyengar1990.gmail.com@kernel.org>]

From: Arun Iyengar <aiyengar1990@gmail.com>

Make the codec-independent VEPU580 programming usable by the coming HEVC
backend, without changing the H.264 programming:

- The encoded picture size alignment (enc_rsl and src_fill) comes from
  the coded format: 16 for H.264, while HEVC uses 8.
- The hardware row rate control takes its codec-specific parameters (QP
  adjustment per deviation bucket, outer threshold multiple, AQ mode)
  from a table. The H.264 one holds the values used so far.
- The row_rc_qp_range module parameter moves to the shared code so that
  both codecs honour it. Its name and default are unchanged.
- Controls shared by several coded formats are registered once.
- The status read-back also collects the inter and intra block counts
  per block size and the lowest and highest QP of the 8x8 block QP
  histogram, for the per-frame statistics.

Signed-off-by: Arun Iyengar <aiyengar1990@gmail.com>
---
 .../media/platform/rockchip/rkvenc/rkvenc-h264.c   | 22 +++++-------
 .../media/platform/rockchip/rkvenc/rkvenc-regs.h   |  7 ++++
 .../platform/rockchip/rkvenc/rkvenc-vepu580.c      | 41 +++++++++++++++-------
 drivers/media/platform/rockchip/rkvenc/rkvenc.c    | 24 ++++++++++---
 drivers/media/platform/rockchip/rkvenc/rkvenc.h    | 41 +++++++++++++++++++++-
 5 files changed, 103 insertions(+), 32 deletions(-)

diff --git a/drivers/media/platform/rockchip/rkvenc/rkvenc-h264.c b/drivers/media/platform/rockchip/rkvenc/rkvenc-h264.c
index c669a6322f29..227d341d060b 100644
--- a/drivers/media/platform/rockchip/rkvenc/rkvenc-h264.c
+++ b/drivers/media/platform/rockchip/rkvenc/rkvenc-h264.c
@@ -12,20 +12,12 @@
  */
 
 #include <linux/bitfield.h>
-#include <linux/moduleparam.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <media/v4l2-h264-enc.h>
 
 #include "rkvenc.h"
 
-#define RKVENC_H264_ROW_QP_RANGE	2
-
-static unsigned int row_rc_qp_range = RKVENC_H264_ROW_QP_RANGE;
-module_param(row_rc_qp_range, uint, 0644);
-MODULE_PARM_DESC(row_rc_qp_range,
-		 "CBR: maximum per-row QP change by the hardware rate control (0 = frame-level rate control only)");
-
 #define RKVENC_H264_PROFILE_BASELINE	66
 #define RKVENC_H264_PROFILE_MAIN	77
 #define RKVENC_H264_PROFILE_HIGH	100
@@ -390,15 +382,16 @@ static int rkvenc_h264_run(struct rkvenc_ctx *ctx, struct rkvenc_core *core,
 	vepu580_setup_h264_tuning(ctx->dev, core, intra);
 
 	/*
-	 * In CBR mode the frame size target from the common rate control is
-	 * handed to the hardware row rate control, which adapts the QP of
-	 * each macroblock row by up to RKVENC_H264_ROW_QP_RANGE.
+	 * In CBR mode the frame size target of the rate control is handed to
+	 * the hardware row rate control, which adapts the QP of each
+	 * macroblock row by up to the row_rc_qp_range parameter.
 	 */
 	h264->hw_rc = rc->mode && rc->mode->type == V4L2_H264_ENC_RC_TYPE_CBR &&
-		      READ_ONCE(row_rc_qp_range);
+		      READ_ONCE(rkvenc_row_rc_qp_range);
 	if (h264->hw_rc)
-		vepu580_setup_row_rc(core, rc->qp, state->qp_min, state->qp_max,
-				     min(READ_ONCE(row_rc_qp_range), 15U),
+		vepu580_setup_row_rc(core, &vepu580_h264_row_rc, rc->qp,
+				     state->qp_min, state->qp_max,
+				     min(READ_ONCE(rkvenc_row_rc_qp_range), 15U),
 				     (u64)rc->size * 8,
 				     mbs, state->width_mbs);
 	else
@@ -506,6 +499,7 @@ static const struct rkvenc_ctrls rkvenc_h264_ctrls = {
 
 const struct rkvenc_coded_fmt_desc rkvenc_h264_fmt_desc = {
 	.fourcc = V4L2_PIX_FMT_H264_SLICE,
+	.size_align = 16,
 	.frmsize = {
 		.min_width = 64,
 		/* The external line buffer for wider pictures is not handled. */
diff --git a/drivers/media/platform/rockchip/rkvenc/rkvenc-regs.h b/drivers/media/platform/rockchip/rkvenc/rkvenc-regs.h
index 6957cdf53446..8103bfdf7151 100644
--- a/drivers/media/platform/rockchip/rkvenc/rkvenc-regs.h
+++ b/drivers/media/platform/rockchip/rkvenc/rkvenc-regs.h
@@ -360,6 +360,11 @@
 #define VEPU580_ST_BUS				0x4030
 #define VEPU580_ST_SNUM				0x4034
 #define VEPU580_ST_SLEN				0x4038
+#define VEPU580_ST_PNUM_P64			0x4100
+#define VEPU580_ST_PNUM_P32			0x4104
+#define VEPU580_ST_PNUM_P16			0x4108
+#define VEPU580_ST_PNUM_P8			0x410c
+#define VEPU580_ST_PNUM_I32			0x4110
 #define VEPU580_ST_PNUM_I16			0x4114
 #define VEPU580_ST_PNUM_I8			0x4118
 #define VEPU580_ST_PNUM_I4			0x411c
@@ -367,6 +372,8 @@
 #define VEPU580_ST_BNUM_CME			0x4124
 #define VEPU580_ST_MADI				0x4128
 #define VEPU580_ST_BNUM_B16			0x412c
+/* Histogram of the QP of the 8x8 blocks, one counter per QP 0..51 */
+#define VEPU580_ST_B8_QP(qp)			(0x4200 + 4 * (qp))
 
 /* Debug class */
 #define VEPU580_DBG_FRAME_CYC			0x5200
diff --git a/drivers/media/platform/rockchip/rkvenc/rkvenc-vepu580.c b/drivers/media/platform/rockchip/rkvenc/rkvenc-vepu580.c
index 33d5154ef8da..3a32caad2216 100644
--- a/drivers/media/platform/rockchip/rkvenc/rkvenc-vepu580.c
+++ b/drivers/media/platform/rockchip/rkvenc/rkvenc-vepu580.c
@@ -12,10 +12,16 @@
 #include <linux/bitfield.h>
 #include <linux/dma-mapping.h>
 #include <linux/minmax.h>
+#include <linux/moduleparam.h>
 #include <linux/slab.h>
 
 #include "rkvenc.h"
 
+unsigned int rkvenc_row_rc_qp_range = 2;
+module_param_named(row_rc_qp_range, rkvenc_row_rc_qp_range, uint, 0644);
+MODULE_PARM_DESC(row_rc_qp_range,
+		 "CBR: maximum per-row QP change by the hardware rate control (0 = frame-level rate control only)");
+
 int rkvenc_alloc_aux(struct rkvenc_dev *rkvenc, struct rkvenc_aux_buf *buf,
 		     size_t size, bool kernel_mapping)
 {
@@ -74,17 +80,18 @@ static void vepu580_setup_src(struct rkvenc_ctx *ctx, struct rkvenc_core *core,
 	struct vb2_buffer *vb = &run->src->vb2_buf;
 	unsigned int width = ctx->coded_fmt.fmt.pix_mp.width;
 	unsigned int height = ctx->coded_fmt.fmt.pix_mp.height;
+	unsigned int align = ctx->coded_fmt_desc->size_align;
 	unsigned int ystride = pix->plane_fmt[0].bytesperline;
 	unsigned int cstride = 0;
 	dma_addr_t addr[3] = { 0 };
 	unsigned int i;
 
 	rkvenc_set(core, VEPU580_ENC_RSL,
-		   FIELD_PREP(VEPU580_ENC_RSL_PIC_WD8_M1, ALIGN(width, 16) / 8 - 1) |
-		   FIELD_PREP(VEPU580_ENC_RSL_PIC_HD8_M1, ALIGN(height, 16) / 8 - 1));
+		   FIELD_PREP(VEPU580_ENC_RSL_PIC_WD8_M1, ALIGN(width, align) / 8 - 1) |
+		   FIELD_PREP(VEPU580_ENC_RSL_PIC_HD8_M1, ALIGN(height, align) / 8 - 1));
 	rkvenc_set(core, VEPU580_SRC_FILL,
-		   FIELD_PREP(VEPU580_SRC_FILL_PIC_WFILL, ALIGN(width, 16) - width) |
-		   FIELD_PREP(VEPU580_SRC_FILL_PIC_HFILL, ALIGN(height, 16) - height));
+		   FIELD_PREP(VEPU580_SRC_FILL_PIC_WFILL, ALIGN(width, align) - width) |
+		   FIELD_PREP(VEPU580_SRC_FILL_PIC_HFILL, ALIGN(height, align) - height));
 
 	/* MPP sets src_range for every YUV input; out_fmt selects 4:2:0. */
 	rkvenc_set(core, VEPU580_SRC_FMT,
@@ -450,17 +457,24 @@ void vepu580_setup_h264_tuning(struct rkvenc_dev *rkvenc,
 }
 
 /*
- * Frame-level QP with the hardware row rate control: each macroblock row
- * gets target_bits / num_blocks bits per block; the cumulative deviation
- * from that target selects one of nine QP adjustments, bounded by
- * qp_range around the frame QP and by [qp_min, qp_max].
+ * Frame-level QP with the hardware row rate control: each block row
+ * (macroblock row for H.264, CTU row for HEVC) gets target_bits /
+ * num_blocks bits per block; the cumulative deviation from that target
+ * selects one of nine QP adjustments, bounded by qp_range around the frame
+ * QP and by [qp_min, qp_max].
  */
-void vepu580_setup_row_rc(struct rkvenc_core *core, unsigned int qp,
+const struct vepu580_row_rc vepu580_h264_row_rc = {
+	.qp_adj = { -2, -1, 0, 1, 2, 0, 0, 0, 1 },
+	.dthd_outer = 4,
+	.aq_mode = false,
+};
+
+void vepu580_setup_row_rc(struct rkvenc_core *core,
+			  const struct vepu580_row_rc *cfg, unsigned int qp,
 			  unsigned int qp_min, unsigned int qp_max,
 			  unsigned int qp_range, u64 target_bits,
 			  unsigned int num_blocks, unsigned int blocks_per_row)
 {
-	static const s8 qp_adj[9] = { -2, -1, 0, 1, 2, 0, 0, 0, 1 };
 	u64 ebit16 = div_u64(target_bits << 4, num_blocks);
 	s32 row_bits, thd;
 	unsigned int i;
@@ -474,6 +488,7 @@ void vepu580_setup_row_rc(struct rkvenc_core *core, unsigned int qp,
 	rkvenc_or(core, VEPU580_ENC_PIC, FIELD_PREP(VEPU580_ENC_PIC_PIC_QP, qp));
 	rkvenc_set(core, VEPU580_RC_CFG,
 		   VEPU580_RC_CFG_RC_EN | VEPU580_RC_CFG_AQ_EN |
+		   (cfg->aq_mode ? VEPU580_RC_CFG_AQ_MODE : 0) |
 		   FIELD_PREP(VEPU580_RC_CFG_RC_CTU_NUM, blocks_per_row));
 	rkvenc_set(core, VEPU580_RC_QP,
 		   FIELD_PREP(VEPU580_RC_QP_RANGE, qp_range) |
@@ -485,12 +500,12 @@ void vepu580_setup_row_rc(struct rkvenc_core *core, unsigned int qp,
 	rkvenc_set(core, VEPU580_RC_ADJ1, 0);
 	for (i = 0; i < 9; i++)
 		rkvenc_or(core, i < 5 ? VEPU580_RC_ADJ0 : VEPU580_RC_ADJ1,
-			  VEPU580_RC_ADJ_QP(i < 5 ? i : i - 5, qp_adj[i]));
+			  VEPU580_RC_ADJ_QP(i < 5 ? i : i - 5, cfg->qp_adj[i]));
 
-	rkvenc_set(core, VEPU580_RC_DTHD(0), -4 * thd);
+	rkvenc_set(core, VEPU580_RC_DTHD(0), -cfg->dthd_outer * thd);
 	rkvenc_set(core, VEPU580_RC_DTHD(1), -thd);
 	rkvenc_set(core, VEPU580_RC_DTHD(2), thd);
-	rkvenc_set(core, VEPU580_RC_DTHD(3), 4 * thd);
+	rkvenc_set(core, VEPU580_RC_DTHD(3), cfg->dthd_outer * thd);
 	for (i = 4; i < 9; i++)
 		rkvenc_set(core, VEPU580_RC_DTHD(i), 0x7fffffff);
 
diff --git a/drivers/media/platform/rockchip/rkvenc/rkvenc.c b/drivers/media/platform/rockchip/rkvenc/rkvenc.c
index 0e5afaefc0dd..623c50db25a8 100644
--- a/drivers/media/platform/rockchip/rkvenc/rkvenc.c
+++ b/drivers/media/platform/rockchip/rkvenc/rkvenc.c
@@ -720,6 +720,7 @@ static void rkvenc_read_feedback(struct rkvenc_core *core,
 {
 	void __iomem *r = core->regs;
 	u32 sse_bsl = readl_relaxed(r + VEPU580_ST_SSE_BSL);
+	unsigned int i;
 
 	fb->bs_len = readl_relaxed(r + VEPU580_ST_BS_LGTH_L32) |
 		     (u64)FIELD_GET(VEPU580_ST_BS_LGTH_H8, sse_bsl) << 32;
@@ -728,9 +729,20 @@ static void rkvenc_read_feedback(struct rkvenc_core *core,
 	fb->qp_sum = readl_relaxed(r + VEPU580_ST_QP_SUM);
 	fb->madi = readl_relaxed(r + VEPU580_ST_MADI);
 	fb->madp = readl_relaxed(r + VEPU580_ST_MADP);
-	fb->intra_blocks = readl_relaxed(r + VEPU580_ST_PNUM_I16) +
-			   readl_relaxed(r + VEPU580_ST_PNUM_I8) +
-			   readl_relaxed(r + VEPU580_ST_PNUM_I4);
+	for (i = 0; i < RKVENC_PNUM_COUNT; i++)
+		fb->pnum[i] = readl_relaxed(r + VEPU580_ST_PNUM_P64 + 4 * i);
+	fb->intra_blocks = fb->pnum[RKVENC_PNUM_I16] + fb->pnum[RKVENC_PNUM_I8] +
+			   fb->pnum[RKVENC_PNUM_I4];
+
+	fb->qp_min = -1;
+	fb->qp_max = -1;
+	for (i = 0; i < 52; i++) {
+		if (!readl_relaxed(r + VEPU580_ST_B8_QP(i)))
+			continue;
+		if (fb->qp_min < 0)
+			fb->qp_min = i;
+		fb->qp_max = i;
+	}
 	fb->cycles = readl_relaxed(r + VEPU580_DBG_FRAME_CYC);
 }
 
@@ -941,8 +953,12 @@ static int rkvenc_init_ctrls(struct rkvenc_ctx *ctx)
 	for (i = 0; i < ARRAY_SIZE(rkvenc_coded_fmts); i++) {
 		const struct rkvenc_ctrls *ctrls = rkvenc_coded_fmts[i]->ctrls;
 
-		for (j = 0; j < ctrls->num_ctrls; j++)
+		for (j = 0; j < ctrls->num_ctrls; j++) {
+			/* Controls shared by several codecs are added once. */
+			if (v4l2_ctrl_find(hdl, ctrls->ctrls[j].id))
+				continue;
 			v4l2_ctrl_new_custom(hdl, &ctrls->ctrls[j], NULL);
+		}
 	}
 
 	ctx->avg_qp_ctrl = v4l2_ctrl_find(hdl, V4L2_CID_MPEG_VIDEO_AVERAGE_QP);
diff --git a/drivers/media/platform/rockchip/rkvenc/rkvenc.h b/drivers/media/platform/rockchip/rkvenc/rkvenc.h
index 83a6084fc084..5bc365101600 100644
--- a/drivers/media/platform/rockchip/rkvenc/rkvenc.h
+++ b/drivers/media/platform/rockchip/rkvenc/rkvenc.h
@@ -53,8 +53,24 @@ struct rkvenc_rec_buf {
 	size_t fbc_hdr_size;
 };
 
+enum rkvenc_pnum {
+	RKVENC_PNUM_P64,
+	RKVENC_PNUM_P32,
+	RKVENC_PNUM_P16,
+	RKVENC_PNUM_P8,
+	RKVENC_PNUM_I32,
+	RKVENC_PNUM_I16,
+	RKVENC_PNUM_I8,
+	RKVENC_PNUM_I4,
+	RKVENC_PNUM_COUNT,
+};
+
 /**
  * struct rkvenc_feedback - per-frame values read back from the status block
+ * @pnum: number of inter (P64..P8) and intra (I32..I4) coded blocks per
+ *	  block size, see &enum rkvenc_pnum
+ * @qp_min: lowest QP of an 8x8 block, -1 when the histogram is empty
+ * @qp_max: highest QP of an 8x8 block, -1 when the histogram is empty
  */
 struct rkvenc_feedback {
 	u32 int_sta;
@@ -64,6 +80,9 @@ struct rkvenc_feedback {
 	u32 madi;
 	u32 madp;
 	u32 intra_blocks;
+	u32 pnum[RKVENC_PNUM_COUNT];
+	int qp_min;
+	int qp_max;
 	u32 cycles;
 };
 
@@ -105,9 +124,12 @@ struct rkvenc_ctrls {
 
 /**
  * struct rkvenc_coded_fmt_desc - coded (CAPTURE) format description
+ * @size_align: alignment of the encoded picture size (enc_rsl), the
+ *		hardware pads the source up to it
  */
 struct rkvenc_coded_fmt_desc {
 	u32 fourcc;
+	unsigned int size_align;
 	struct v4l2_frmsize_stepwise frmsize;
 	const struct rkvenc_ctrls *ctrls;
 	const struct rkvenc_codec_ops *ops;
@@ -222,7 +244,24 @@ void vepu580_setup_me(struct rkvenc_core *core, unsigned int width_mbs,
 		      bool intra);
 void vepu580_setup_h264_tuning(struct rkvenc_dev *rkvenc,
 			       struct rkvenc_core *core, bool intra);
-void vepu580_setup_row_rc(struct rkvenc_core *core, unsigned int qp,
+
+/**
+ * struct vepu580_row_rc - codec-specific row rate control parameters
+ * @qp_adj: QP adjustment for each of the nine deviation buckets
+ * @dthd_outer: multiple of the base threshold for the outer buckets
+ * @aq_mode: value of rc_cfg.aq_mode
+ */
+struct vepu580_row_rc {
+	s8 qp_adj[9];
+	unsigned int dthd_outer;
+	bool aq_mode;
+};
+
+extern const struct vepu580_row_rc vepu580_h264_row_rc;
+extern unsigned int rkvenc_row_rc_qp_range;
+
+void vepu580_setup_row_rc(struct rkvenc_core *core,
+			  const struct vepu580_row_rc *cfg, unsigned int qp,
 			  unsigned int qp_min, unsigned int qp_max,
 			  unsigned int qp_range, u64 target_bits,
 			  unsigned int num_blocks, unsigned int blocks_per_row);

-- 
2.55.0