[PATCH v2 12/13] media: verisilicon: Enable AV1 decoder on rk3588

From: Benjamin Gaignard
Date: Tue Jan 03 2023 - 12:05:43 EST


Add rk3588 AV1 decoder to Hantro variant.
The hardware support image from 64x64 up to 7680x4320
by steps of 16 pixels.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@xxxxxxxxxxxxx>
---
.../media/platform/verisilicon/hantro_drv.c | 1 +
.../media/platform/verisilicon/hantro_hw.h | 6 +
.../platform/verisilicon/rockchip_vpu_hw.c | 119 ++++++++++++++++++
3 files changed, 126 insertions(+)

diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c
index 16539e89935c..4fc6dea16ae6 100644
--- a/drivers/media/platform/verisilicon/hantro_drv.c
+++ b/drivers/media/platform/verisilicon/hantro_drv.c
@@ -688,6 +688,7 @@ static const struct of_device_id of_hantro_match[] = {
{ .compatible = "rockchip,rk3399-vpu", .data = &rk3399_vpu_variant, },
{ .compatible = "rockchip,rk3568-vepu", .data = &rk3568_vepu_variant, },
{ .compatible = "rockchip,rk3568-vpu", .data = &rk3568_vpu_variant, },
+ { .compatible = "rockchip,rk3588-av1-vpu", .data = &rk3588_vpu981_variant, },
#endif
#ifdef CONFIG_VIDEO_HANTRO_IMX8M
{ .compatible = "nxp,imx8mm-vpu-g1", .data = &imx8mm_vpu_g1_variant, },
diff --git a/drivers/media/platform/verisilicon/hantro_hw.h b/drivers/media/platform/verisilicon/hantro_hw.h
index ad1b39d65683..79cbd27f676c 100644
--- a/drivers/media/platform/verisilicon/hantro_hw.h
+++ b/drivers/media/platform/verisilicon/hantro_hw.h
@@ -404,11 +404,13 @@ extern const struct hantro_variant rk3328_vpu_variant;
extern const struct hantro_variant rk3399_vpu_variant;
extern const struct hantro_variant rk3568_vepu_variant;
extern const struct hantro_variant rk3568_vpu_variant;
+extern const struct hantro_variant rk3588_vpu981_variant;
extern const struct hantro_variant sama5d4_vdec_variant;
extern const struct hantro_variant sunxi_vpu_variant;

extern const struct hantro_postproc_ops hantro_g1_postproc_ops;
extern const struct hantro_postproc_ops hantro_g2_postproc_ops;
+extern const struct hantro_postproc_ops rockchip_vpu981_postproc_ops;

extern const u32 hantro_vp8_dec_mc_filter[8][6];

@@ -445,6 +447,10 @@ void hantro_hevc_ref_init(struct hantro_ctx *ctx);
dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx, s32 poc);
int hantro_hevc_add_ref_buf(struct hantro_ctx *ctx, int poc, dma_addr_t addr);

+int rockchip_vpu981_av1_dec_init(struct hantro_ctx *ctx);
+void rockchip_vpu981_av1_dec_exit(struct hantro_ctx *ctx);
+int rockchip_vpu981_av1_dec_run(struct hantro_ctx *ctx);
+void rockchip_vpu981_av1_dec_done(struct hantro_ctx *ctx);

static inline unsigned short hantro_vp9_num_sbs(unsigned short dimension)
{
diff --git a/drivers/media/platform/verisilicon/rockchip_vpu_hw.c b/drivers/media/platform/verisilicon/rockchip_vpu_hw.c
index 8de6fd2e8eef..b0b66a13f9ec 100644
--- a/drivers/media/platform/verisilicon/rockchip_vpu_hw.c
+++ b/drivers/media/platform/verisilicon/rockchip_vpu_hw.c
@@ -13,9 +13,13 @@
#include "hantro_g1_regs.h"
#include "hantro_h1_regs.h"
#include "rockchip_vpu2_regs.h"
+#include "rockchip_vpu981_regs.h"

#define RK3066_ACLK_MAX_FREQ (300 * 1000 * 1000)
#define RK3288_ACLK_MAX_FREQ (400 * 1000 * 1000)
+#define RK3588_ACLK_MAX_FREQ (300 * 1000 * 1000)
+
+#define ROCKCHIP_VPU981_MIN_SIZE 64

/*
* Supported formats.
@@ -74,6 +78,22 @@ static const struct hantro_fmt rockchip_vpu1_postproc_fmts[] = {
},
};

+static const struct hantro_fmt rockchip_vpu981_postproc_fmts[] = {
+ {
+ .fourcc = V4L2_PIX_FMT_NV12,
+ .codec_mode = HANTRO_MODE_NONE,
+ .postprocessed = true,
+ .frmsize = {
+ .min_width = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_width = FMT_UHD_WIDTH,
+ .step_width = MB_DIM,
+ .min_height = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_height = FMT_UHD_HEIGHT,
+ .step_height = MB_DIM,
+ },
+ },
+};
+
static const struct hantro_fmt rk3066_vpu_dec_fmts[] = {
{
.fourcc = V4L2_PIX_FMT_NV12,
@@ -277,6 +297,48 @@ static const struct hantro_fmt rk3399_vpu_dec_fmts[] = {
},
};

+static const struct hantro_fmt rockchip_vpu981_dec_fmts[] = {
+ {
+ .fourcc = V4L2_PIX_FMT_NV12_4L4,
+ .codec_mode = HANTRO_MODE_NONE,
+ .match_depth = true,
+ .frmsize = {
+ .min_width = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_width = FMT_UHD_WIDTH,
+ .step_width = MB_DIM,
+ .min_height = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_height = FMT_UHD_HEIGHT,
+ .step_height = MB_DIM,
+ },
+ },
+ {
+ .fourcc = V4L2_PIX_FMT_NV12_10LE40_4L4,
+ .codec_mode = HANTRO_MODE_NONE,
+ .match_depth = true,
+ .frmsize = {
+ .min_width = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_width = FMT_UHD_WIDTH,
+ .step_width = MB_DIM,
+ .min_height = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_height = FMT_UHD_HEIGHT,
+ .step_height = MB_DIM,
+ },
+ },
+ {
+ .fourcc = V4L2_PIX_FMT_AV1_FRAME,
+ .codec_mode = HANTRO_MODE_AV1_DEC,
+ .max_depth = 2,
+ .frmsize = {
+ .min_width = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_width = FMT_UHD_WIDTH,
+ .step_width = MB_DIM,
+ .min_height = ROCKCHIP_VPU981_MIN_SIZE,
+ .max_height = FMT_UHD_HEIGHT,
+ .step_height = MB_DIM,
+ },
+ },
+};
+
static irqreturn_t rockchip_vpu1_vepu_irq(int irq, void *dev_id)
{
struct hantro_dev *vpu = dev_id;
@@ -331,6 +393,24 @@ static irqreturn_t rockchip_vpu2_vepu_irq(int irq, void *dev_id)
return IRQ_HANDLED;
}

+static irqreturn_t rk3588_vpu981_irq(int irq, void *dev_id)
+{
+ struct hantro_dev *vpu = dev_id;
+ enum vb2_buffer_state state;
+ u32 status;
+
+ status = vdpu_read(vpu, AV1_REG_INTERRUPT);
+ state = (status & AV1_REG_INTERRUPT_DEC_RDY_INT) ?
+ VB2_BUF_STATE_DONE : VB2_BUF_STATE_ERROR;
+
+ vdpu_write(vpu, 0, AV1_REG_INTERRUPT);
+ vdpu_write(vpu, AV1_REG_CONFIG_DEC_CLK_GATE_E, AV1_REG_CONFIG);
+
+ hantro_irq_done(vpu, state);
+
+ return IRQ_HANDLED;
+}
+
static int rk3036_vpu_hw_init(struct hantro_dev *vpu)
{
/* Bump ACLK to max. possible freq. to improve performance. */
@@ -346,6 +426,13 @@ static int rk3066_vpu_hw_init(struct hantro_dev *vpu)
return 0;
}

+static int rk3588_vpu981_hw_init(struct hantro_dev *vpu)
+{
+ /* Bump ACLKs to max. possible freq. to improve performance. */
+ clk_set_rate(vpu->clocks[0].clk, RK3588_ACLK_MAX_FREQ);
+ return 0;
+}
+
static int rockchip_vpu_hw_init(struct hantro_dev *vpu)
{
/* Bump ACLK to max. possible freq. to improve performance. */
@@ -498,6 +585,14 @@ static const struct hantro_codec_ops rk3568_vepu_codec_ops[] = {
},
};

+static const struct hantro_codec_ops rk3588_vpu981_codec_ops[] = {
+ [HANTRO_MODE_AV1_DEC] = {
+ .run = rockchip_vpu981_av1_dec_run,
+ .init = rockchip_vpu981_av1_dec_init,
+ .exit = rockchip_vpu981_av1_dec_exit,
+ .done = rockchip_vpu981_av1_dec_done,
+ },
+};
/*
* VPU variant.
*/
@@ -529,10 +624,18 @@ static const char * const rk3066_vpu_clk_names[] = {
"aclk_vepu", "hclk_vepu"
};

+static const struct hantro_irq rk3588_vpu981_irqs[] = {
+ { "vdpu", rk3588_vpu981_irq },
+};
+
static const char * const rockchip_vpu_clk_names[] = {
"aclk", "hclk"
};

+static const char * const rk3588_vpu981_vpu_clk_names[] = {
+ "aclk", "hclk", "aclk_vdpu_root", "hclk_vdpu_root"
+};
+
/* VDPU1/VEPU1 */

const struct hantro_variant rk3036_vpu_variant = {
@@ -678,3 +781,19 @@ const struct hantro_variant px30_vpu_variant = {
.clk_names = rockchip_vpu_clk_names,
.num_clocks = ARRAY_SIZE(rockchip_vpu_clk_names)
};
+
+const struct hantro_variant rk3588_vpu981_variant = {
+ .dec_offset = 0x0,
+ .dec_fmts = rockchip_vpu981_dec_fmts,
+ .num_dec_fmts = ARRAY_SIZE(rockchip_vpu981_dec_fmts),
+ .postproc_fmts = rockchip_vpu981_postproc_fmts,
+ .num_postproc_fmts = ARRAY_SIZE(rockchip_vpu981_postproc_fmts),
+ .postproc_ops = &rockchip_vpu981_postproc_ops,
+ .codec = HANTRO_AV1_DECODER,
+ .codec_ops = rk3588_vpu981_codec_ops,
+ .irqs = rk3588_vpu981_irqs,
+ .num_irqs = ARRAY_SIZE(rk3588_vpu981_irqs),
+ .init = rk3588_vpu981_hw_init,
+ .clk_names = rk3588_vpu981_vpu_clk_names,
+ .num_clocks = ARRAY_SIZE(rk3588_vpu981_vpu_clk_names)
+};
--
2.34.1