media: add Rockchip VPU JPEG encoder driver

Add a mem2mem driver for the VPU available on Rockchip SoCs.
Currently only JPEG encoding is supported, for RK3399 and RK3288
platforms.
Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
[hverkuil-cisco@xs4all.nl: fix checkpatch.pl alignment warning]
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>

MAINTAINERS

@@ -12841,6 +12841,13 @@ S:	Maintained
 F:	drivers/media/platform/rockchip/rga/
 F:	Documentation/devicetree/bindings/media/rockchip-rga.txt
 
+ROCKCHIP VPU CODEC DRIVER
+M:	Ezequiel Garcia <ezequiel@collabora.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/staging/media/platform/rockchip/vpu/
+F:	Documentation/devicetree/bindings/media/rockchip-vpu.txt
+
 ROCKER DRIVER
 M:	Jiri Pirko <jiri@resnulli.us>
 L:	netdev@vger.kernel.org

drivers/staging/media/Kconfig

@@ -31,6 +31,8 @@ source "drivers/staging/media/mt9t031/Kconfig"
 
 source "drivers/staging/media/omap4iss/Kconfig"
 
+source "drivers/staging/media/rockchip/vpu/Kconfig"
+
 source "drivers/staging/media/sunxi/Kconfig"
 
 source "drivers/staging/media/tegra-vde/Kconfig"

drivers/staging/media/Makefile

@@ -8,3 +8,4 @@ obj-$(CONFIG_VIDEO_OMAP4)	+= omap4iss/
 obj-$(CONFIG_VIDEO_SUNXI)	+= sunxi/
 obj-$(CONFIG_TEGRA_VDE)		+= tegra-vde/
 obj-$(CONFIG_VIDEO_ZORAN)	+= zoran/
+obj-$(CONFIG_VIDEO_ROCKCHIP_VPU) += rockchip/vpu/

drivers/staging/media/rockchip/vpu/Kconfig

+config VIDEO_ROCKCHIP_VPU
+	tristate "Rockchip VPU driver"
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	depends on VIDEO_DEV && VIDEO_V4L2 && MEDIA_CONTROLLER
+	select VIDEOBUF2_DMA_CONTIG
+	select VIDEOBUF2_VMALLOC
+	select V4L2_MEM2MEM_DEV
+	default n
+	help
+	  Support for the Video Processing Unit present on Rockchip SoC,
+	  which accelerates video and image encoding and decoding.
+	  To compile this driver as a module, choose M here: the module
+	  will be called rockchip-vpu.

drivers/staging/media/rockchip/vpu/Makefile

+obj-$(CONFIG_VIDEO_ROCKCHIP_VPU) += rockchip-vpu.o
+
+rockchip-vpu-y += \
+		rockchip_vpu_drv.o \
+		rockchip_vpu_enc.o \
+		rk3288_vpu_hw.o \
+		rk3288_vpu_hw_jpeg_enc.o \
+		rk3399_vpu_hw.o \
+		rk3399_vpu_hw_jpeg_enc.o \
+		rockchip_vpu_jpeg.o

drivers/staging/media/rockchip/vpu/TODO

+* Support for VP8, VP9 and H264 is planned for this driver.
+
+  Given the V4L controls for those CODECs will be part of
+  the uABI, it will be required to have the driver in staging.
+
+  For this reason, we are keeping this driver in staging for now.
+
+* Add support for the S_SELECTION API.
+  See the comment for VEPU_REG_ENC_OVER_FILL_STRM_OFFSET.
+
+* Instead of having a DMA bounce buffer, it could be possible to use a
+  normal buffer and memmove() the payload to make space for the header.
+  This might need to use extra JPEG markers for padding reasons.

drivers/staging/media/rockchip/vpu/rk3288_vpu_hw.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright (C) 2018 Rockchip Electronics Co., Ltd.
+ *	Jeffy Chen <jeffy.chen@rock-chips.com>
+ */
+
+#include <linux/clk.h>
+
+#include "rockchip_vpu.h"
+#include "rockchip_vpu_jpeg.h"
+#include "rk3288_vpu_regs.h"
+
+#define RK3288_ACLK_MAX_FREQ (400 * 1000 * 1000)
+
+/*
+ * Supported formats.
+ */
+
+static const struct rockchip_vpu_fmt rk3288_vpu_enc_fmts[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_YUV420M,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_YUV420P,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_YUV420SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YUYV,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_YUYV422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_UYVY,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_UYVY422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_JPEG,
+		.codec_mode = RK_VPU_MODE_JPEG_ENC,
+		.max_depth = 2,
+		.header_size = JPEG_HEADER_SIZE,
+		.frmsize = {
+			.min_width = 96,
+			.max_width = 8192,
+			.step_width = JPEG_MB_DIM,
+			.min_height = 32,
+			.max_height = 8192,
+			.step_height = JPEG_MB_DIM,
+		},
+	},
+};
+
+static irqreturn_t rk3288_vepu_irq(int irq, void *dev_id)
+{
+	struct rockchip_vpu_dev *vpu = dev_id;
+	enum vb2_buffer_state state;
+	u32 status, bytesused;
+
+	status = vepu_read(vpu, VEPU_REG_INTERRUPT);
+	bytesused = vepu_read(vpu, VEPU_REG_STR_BUF_LIMIT) / 8;
+	state = (status & VEPU_REG_INTERRUPT_FRAME_RDY) ?
+		VB2_BUF_STATE_DONE : VB2_BUF_STATE_ERROR;
+
+	vepu_write(vpu, 0, VEPU_REG_INTERRUPT);
+	vepu_write(vpu, 0, VEPU_REG_AXI_CTRL);
+
+	rockchip_vpu_irq_done(vpu, bytesused, state);
+
+	return IRQ_HANDLED;
+}
+
+static int rk3288_vpu_hw_init(struct rockchip_vpu_dev *vpu)
+{
+	/* Bump ACLK to max. possible freq. to improve performance. */
+	clk_set_rate(vpu->clocks[0].clk, RK3288_ACLK_MAX_FREQ);
+	return 0;
+}
+
+static void rk3288_vpu_enc_reset(struct rockchip_vpu_ctx *ctx)
+{
+	struct rockchip_vpu_dev *vpu = ctx->dev;
+
+	vepu_write(vpu, VEPU_REG_INTERRUPT_DIS_BIT, VEPU_REG_INTERRUPT);
+	vepu_write(vpu, 0, VEPU_REG_ENC_CTRL);
+	vepu_write(vpu, 0, VEPU_REG_AXI_CTRL);
+}
+
+/*
+ * Supported codec ops.
+ */
+
+static const struct rockchip_vpu_codec_ops rk3288_vpu_codec_ops[] = {
+	[RK_VPU_MODE_JPEG_ENC] = {
+		.run = rk3288_vpu_jpeg_enc_run,
+		.reset = rk3288_vpu_enc_reset,
+	},
+};
+
+/*
+ * VPU variant.
+ */
+
+const struct rockchip_vpu_variant rk3288_vpu_variant = {
+	.enc_offset = 0x0,
+	.enc_fmts = rk3288_vpu_enc_fmts,
+	.num_enc_fmts = ARRAY_SIZE(rk3288_vpu_enc_fmts),
+	.codec_ops = rk3288_vpu_codec_ops,
+	.codec = RK_VPU_CODEC_JPEG,
+	.vepu_irq = rk3288_vepu_irq,
+	.init = rk3288_vpu_hw_init,
+	.clk_names = {"aclk", "hclk"},
+	.num_clocks = 2
+};

drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright (C) 2018 Rockchip Electronics Co., Ltd.
+ */
+
+#include <asm/unaligned.h>
+#include <media/v4l2-mem2mem.h>
+#include "rockchip_vpu_jpeg.h"
+#include "rockchip_vpu.h"
+#include "rockchip_vpu_common.h"
+#include "rockchip_vpu_hw.h"
+#include "rk3288_vpu_regs.h"
+
+#define VEPU_JPEG_QUANT_TABLE_COUNT 16
+
+static void rk3288_vpu_set_src_img_ctrl(struct rockchip_vpu_dev *vpu,
+					struct rockchip_vpu_ctx *ctx)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &ctx->src_fmt;
+	u32 reg;
+
+	reg = VEPU_REG_IN_IMG_CTRL_ROW_LEN(pix_fmt->width)
+		| VEPU_REG_IN_IMG_CTRL_OVRFLR_D4(0)
+		| VEPU_REG_IN_IMG_CTRL_OVRFLB_D4(0)
+		| VEPU_REG_IN_IMG_CTRL_FMT(ctx->vpu_src_fmt->enc_fmt);
+	vepu_write_relaxed(vpu, reg, VEPU_REG_IN_IMG_CTRL);
+}
+
+static void rk3288_vpu_jpeg_enc_set_buffers(struct rockchip_vpu_dev *vpu,
+					    struct rockchip_vpu_ctx *ctx,
+					    struct vb2_buffer *src_buf)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &ctx->src_fmt;
+	dma_addr_t src[3];
+
+	WARN_ON(pix_fmt->num_planes > 3);
+
+	vepu_write_relaxed(vpu, ctx->bounce_dma_addr,
+			   VEPU_REG_ADDR_OUTPUT_STREAM);
+	vepu_write_relaxed(vpu, ctx->bounce_size,
+			   VEPU_REG_STR_BUF_LIMIT);
+
+	if (pix_fmt->num_planes == 1) {
+		src[0] = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+		/* single plane formats we supported are all interlaced */
+		vepu_write_relaxed(vpu, src[0], VEPU_REG_ADDR_IN_PLANE_0);
+	} else if (pix_fmt->num_planes == 2) {
+		src[0] = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+		src[1] = vb2_dma_contig_plane_dma_addr(src_buf, 1);
+		vepu_write_relaxed(vpu, src[0], VEPU_REG_ADDR_IN_PLANE_0);
+		vepu_write_relaxed(vpu, src[1], VEPU_REG_ADDR_IN_PLANE_1);
+	} else {
+		src[0] = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+		src[1] = vb2_dma_contig_plane_dma_addr(src_buf, 1);
+		src[2] = vb2_dma_contig_plane_dma_addr(src_buf, 2);
+		vepu_write_relaxed(vpu, src[0], VEPU_REG_ADDR_IN_PLANE_0);
+		vepu_write_relaxed(vpu, src[1], VEPU_REG_ADDR_IN_PLANE_1);
+		vepu_write_relaxed(vpu, src[2], VEPU_REG_ADDR_IN_PLANE_2);
+	}
+}
+
+static void
+rk3288_vpu_jpeg_enc_set_qtable(struct rockchip_vpu_dev *vpu,
+			       unsigned char *luma_qtable,
+			       unsigned char *chroma_qtable)
+{
+	__be32 *luma_qtable_p;
+	__be32 *chroma_qtable_p;
+	u32 reg, i;
+
+	luma_qtable_p = (__be32 *)luma_qtable;
+	chroma_qtable_p = (__be32 *)chroma_qtable;
+
+	for (i = 0; i < VEPU_JPEG_QUANT_TABLE_COUNT; i++) {
+		reg = get_unaligned_be32(&luma_qtable[i]);
+		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_LUMA_QUAT(i));
+
+		reg = get_unaligned_be32(&chroma_qtable[i]);
+		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_CHROMA_QUAT(i));
+	}
+}
+
+void rk3288_vpu_jpeg_enc_run(struct rockchip_vpu_ctx *ctx)
+{
+	struct rockchip_vpu_dev *vpu = ctx->dev;
+	struct vb2_buffer *src_buf, *dst_buf;
+	struct rockchip_vpu_jpeg_ctx jpeg_ctx;
+	u32 reg;
+
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+
+	memset(&jpeg_ctx, 0, sizeof(jpeg_ctx));
+	jpeg_ctx.buffer = vb2_plane_vaddr(dst_buf, 0);
+	jpeg_ctx.width = ctx->dst_fmt.width;
+	jpeg_ctx.height = ctx->dst_fmt.height;
+	jpeg_ctx.quality = ctx->jpeg_quality;
+	rockchip_vpu_jpeg_header_assemble(&jpeg_ctx);
+
+	/* Switch to JPEG encoder mode before writing registers */
+	vepu_write_relaxed(vpu, VEPU_REG_ENC_CTRL_ENC_MODE_JPEG,
+			   VEPU_REG_ENC_CTRL);
+
+	rk3288_vpu_set_src_img_ctrl(vpu, ctx);
+	rk3288_vpu_jpeg_enc_set_buffers(vpu, ctx, src_buf);
+	rk3288_vpu_jpeg_enc_set_qtable(vpu,
+		rockchip_vpu_jpeg_get_qtable(&jpeg_ctx, 0),
+		rockchip_vpu_jpeg_get_qtable(&jpeg_ctx, 1));
+
+	reg = VEPU_REG_AXI_CTRL_OUTPUT_SWAP16
+		| VEPU_REG_AXI_CTRL_INPUT_SWAP16
+		| VEPU_REG_AXI_CTRL_BURST_LEN(16)
+		| VEPU_REG_AXI_CTRL_OUTPUT_SWAP32
+		| VEPU_REG_AXI_CTRL_INPUT_SWAP32
+		| VEPU_REG_AXI_CTRL_OUTPUT_SWAP8
+		| VEPU_REG_AXI_CTRL_INPUT_SWAP8;
+	/* Make sure that all registers are written at this point. */
+	vepu_write(vpu, reg, VEPU_REG_AXI_CTRL);
+
+	reg = VEPU_REG_ENC_CTRL_WIDTH(JPEG_MB_WIDTH(ctx->src_fmt.width))
+		| VEPU_REG_ENC_CTRL_HEIGHT(JPEG_MB_HEIGHT(ctx->src_fmt.height))
+		| VEPU_REG_ENC_CTRL_ENC_MODE_JPEG
+		| VEPU_REG_ENC_PIC_INTRA
+		| VEPU_REG_ENC_CTRL_EN_BIT;
+	/* Kick the watchdog and start encoding */
+	schedule_delayed_work(&vpu->watchdog_work, msecs_to_jiffies(2000));
+	vepu_write(vpu, reg, VEPU_REG_ENC_CTRL);
+}

drivers/staging/media/rockchip/vpu/rk3399_vpu_hw.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright (C) 2018 Rockchip Electronics Co., Ltd.
+ *	Jeffy Chen <jeffy.chen@rock-chips.com>
+ */
+
+#include <linux/clk.h>
+
+#include "rockchip_vpu.h"
+#include "rockchip_vpu_jpeg.h"
+#include "rk3399_vpu_regs.h"
+
+#define RK3399_ACLK_MAX_FREQ (400 * 1000 * 1000)
+
+/*
+ * Supported formats.
+ */
+
+static const struct rockchip_vpu_fmt rk3399_vpu_enc_fmts[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_YUV420M,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_YUV420P,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_YUV420SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YUYV,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_YUYV422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_UYVY,
+		.codec_mode = RK_VPU_MODE_NONE,
+		.enc_fmt = RK3288_VPU_ENC_FMT_UYVY422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_JPEG,
+		.codec_mode = RK_VPU_MODE_JPEG_ENC,
+		.max_depth = 2,
+		.header_size = JPEG_HEADER_SIZE,
+		.frmsize = {
+			.min_width = 96,
+			.max_width = 8192,
+			.step_width = JPEG_MB_DIM,
+			.min_height = 32,
+			.max_height = 8192,
+			.step_height = JPEG_MB_DIM,
+		},
+	},
+};
+
+static irqreturn_t rk3399_vepu_irq(int irq, void *dev_id)
+{
+	struct rockchip_vpu_dev *vpu = dev_id;
+	enum vb2_buffer_state state;
+	u32 status, bytesused;
+
+	status = vepu_read(vpu, VEPU_REG_INTERRUPT);
+	bytesused = vepu_read(vpu, VEPU_REG_STR_BUF_LIMIT) / 8;
+	state = (status & VEPU_REG_INTERRUPT_FRAME_READY) ?
+		VB2_BUF_STATE_DONE : VB2_BUF_STATE_ERROR;
+
+	vepu_write(vpu, 0, VEPU_REG_INTERRUPT);
+	vepu_write(vpu, 0, VEPU_REG_AXI_CTRL);
+
+	rockchip_vpu_irq_done(vpu, bytesused, state);
+
+	return IRQ_HANDLED;
+}
+
+static int rk3399_vpu_hw_init(struct rockchip_vpu_dev *vpu)
+{
+	/* Bump ACLK to max. possible freq. to improve performance. */
+	clk_set_rate(vpu->clocks[0].clk, RK3399_ACLK_MAX_FREQ);
+	return 0;
+}
+
+static void rk3399_vpu_enc_reset(struct rockchip_vpu_ctx *ctx)
+{
+	struct rockchip_vpu_dev *vpu = ctx->dev;
+
+	vepu_write(vpu, VEPU_REG_INTERRUPT_DIS_BIT, VEPU_REG_INTERRUPT);
+	vepu_write(vpu, 0, VEPU_REG_ENCODE_START);
+	vepu_write(vpu, 0, VEPU_REG_AXI_CTRL);
+}
+
+/*
+ * Supported codec ops.
+ */
+
+static const struct rockchip_vpu_codec_ops rk3399_vpu_codec_ops[] = {
+	[RK_VPU_MODE_JPEG_ENC] = {
+		.run = rk3399_vpu_jpeg_enc_run,
+		.reset = rk3399_vpu_enc_reset,
+	},
+};
+
+/*
+ * VPU variant.
+ */
+
+const struct rockchip_vpu_variant rk3399_vpu_variant = {
+	.enc_offset = 0x0,
+	.enc_fmts = rk3399_vpu_enc_fmts,
+	.num_enc_fmts = ARRAY_SIZE(rk3399_vpu_enc_fmts),
+	.codec = RK_VPU_CODEC_JPEG,
+	.codec_ops = rk3399_vpu_codec_ops,
+	.vepu_irq = rk3399_vepu_irq,
+	.init = rk3399_vpu_hw_init,
+	.clk_names = {"aclk", "hclk"},
+	.num_clocks = 2
+};

drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright (C) 2018 Rockchip Electronics Co., Ltd.
+ *
+ * JPEG encoder
+ * ------------
+ * The VPU JPEG encoder produces JPEG baseline sequential format.
+ * The quantization coefficients are 8-bit values, complying with
+ * the baseline specification. Therefore, it requires
+ * luma and chroma quantization tables. The hardware does entropy
+ * encoding using internal Huffman tables, as specified in the JPEG
+ * specification.
+ *
+ * In other words, only the luma and chroma quantization tables are
+ * required for the encoding operation.
+ *
+ * Quantization luma table values are written to registers
+ * VEPU_swreg_0-VEPU_swreg_15, and chroma table values to
+ * VEPU_swreg_16-VEPU_swreg_31.
+ *
+ * JPEG zigzag order is expected on the quantization tables.
+ */
+
+#include <asm/unaligned.h>
+#include <media/v4l2-mem2mem.h>
+#include "rockchip_vpu_jpeg.h"
+#include "rockchip_vpu.h"
+#include "rockchip_vpu_common.h"
+#include "rockchip_vpu_hw.h"
+#include "rk3399_vpu_regs.h"
+
+#define VEPU_JPEG_QUANT_TABLE_COUNT 16
+
+static void rk3399_vpu_set_src_img_ctrl(struct rockchip_vpu_dev *vpu,
+					struct rockchip_vpu_ctx *ctx)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &ctx->src_fmt;
+	u32 reg;
+
+	/*
+	 * The pix fmt width/height are already macroblock aligned
+	 * by .vidioc_s_fmt_vid_cap_mplane() callback
+	 */
+	reg = VEPU_REG_IN_IMG_CTRL_ROW_LEN(pix_fmt->width);
+	vepu_write_relaxed(vpu, reg, VEPU_REG_INPUT_LUMA_INFO);
+
+	reg = VEPU_REG_IN_IMG_CTRL_OVRFLR_D4(0) |
+	      VEPU_REG_IN_IMG_CTRL_OVRFLB(0);
+	/*
+	 * This register controls the input crop, as the offset
+	 * from the right/bottom within the last macroblock. The offset from the
+	 * right must be divided by 4 and so the crop must be aligned to 4 pixels
+	 * horizontally.
+	 */
+	vepu_write_relaxed(vpu, reg, VEPU_REG_ENC_OVER_FILL_STRM_OFFSET);
+
+	reg = VEPU_REG_IN_IMG_CTRL_FMT(ctx->vpu_src_fmt->enc_fmt);
+	vepu_write_relaxed(vpu, reg, VEPU_REG_ENC_CTRL1);
+}
+
+static void rk3399_vpu_jpeg_enc_set_buffers(struct rockchip_vpu_dev *vpu,
+					    struct rockchip_vpu_ctx *ctx,
+					    struct vb2_buffer *src_buf)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &ctx->src_fmt;
+	dma_addr_t src[3];
+
+	WARN_ON(pix_fmt->num_planes > 3);
+
+	vepu_write_relaxed(vpu, ctx->bounce_dma_addr,
+			   VEPU_REG_ADDR_OUTPUT_STREAM);
+	vepu_write_relaxed(vpu, ctx->bounce_size,
+			   VEPU_REG_STR_BUF_LIMIT);
+
+	if (pix_fmt->num_planes == 1) {
+		src[0] = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+		vepu_write_relaxed(vpu, src[0], VEPU_REG_ADDR_IN_PLANE_0);
+	} else if (pix_fmt->num_planes == 2) {
+		src[0] = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+		src[1] = vb2_dma_contig_plane_dma_addr(src_buf, 1);
+		vepu_write_relaxed(vpu, src[0], VEPU_REG_ADDR_IN_PLANE_0);
+		vepu_write_relaxed(vpu, src[1], VEPU_REG_ADDR_IN_PLANE_1);
+	} else {
+		src[0] = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+		src[1] = vb2_dma_contig_plane_dma_addr(src_buf, 1);
+		src[2] = vb2_dma_contig_plane_dma_addr(src_buf, 2);
+		vepu_write_relaxed(vpu, src[0], VEPU_REG_ADDR_IN_PLANE_0);
+		vepu_write_relaxed(vpu, src[1], VEPU_REG_ADDR_IN_PLANE_1);
+		vepu_write_relaxed(vpu, src[2], VEPU_REG_ADDR_IN_PLANE_2);
+	}
+}
+
+static void
+rk3399_vpu_jpeg_enc_set_qtable(struct rockchip_vpu_dev *vpu,
+			       unsigned char *luma_qtable,
+			       unsigned char *chroma_qtable)
+{
+	__be32 *luma_qtable_p;
+	__be32 *chroma_qtable_p;
+	u32 reg, i;
+
+	luma_qtable_p = (__be32 *)luma_qtable;
+	chroma_qtable_p = (__be32 *)chroma_qtable;
+
+	for (i = 0; i < VEPU_JPEG_QUANT_TABLE_COUNT; i++) {
+		reg = get_unaligned_be32(&luma_qtable[i]);
+		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_LUMA_QUAT(i));
+
+		reg = get_unaligned_be32(&chroma_qtable[i]);
+		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_CHROMA_QUAT(i));
+	}
+}
+
+void rk3399_vpu_jpeg_enc_run(struct rockchip_vpu_ctx *ctx)
+{
+	struct rockchip_vpu_dev *vpu = ctx->dev;
+	struct vb2_buffer *src_buf, *dst_buf;
+	struct rockchip_vpu_jpeg_ctx jpeg_ctx;
+	u32 reg;
+
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+
+	memset(&jpeg_ctx, 0, sizeof(jpeg_ctx));
+	jpeg_ctx.buffer = vb2_plane_vaddr(dst_buf, 0);
+	jpeg_ctx.width = ctx->dst_fmt.width;
+	jpeg_ctx.height = ctx->dst_fmt.height;
+	jpeg_ctx.quality = ctx->jpeg_quality;
+	rockchip_vpu_jpeg_header_assemble(&jpeg_ctx);
+
+	/* Switch to JPEG encoder mode before writing registers */
+	vepu_write_relaxed(vpu, VEPU_REG_ENCODE_FORMAT_JPEG,
+			   VEPU_REG_ENCODE_START);
+
+	rk3399_vpu_set_src_img_ctrl(vpu, ctx);
+	rk3399_vpu_jpeg_enc_set_buffers(vpu, ctx, src_buf);
+	rk3399_vpu_jpeg_enc_set_qtable(vpu,
+			rockchip_vpu_jpeg_get_qtable(&jpeg_ctx, 0),
+			rockchip_vpu_jpeg_get_qtable(&jpeg_ctx, 1));
+
+	reg = VEPU_REG_OUTPUT_SWAP32
+		| VEPU_REG_OUTPUT_SWAP16
+		| VEPU_REG_OUTPUT_SWAP8
+		| VEPU_REG_INPUT_SWAP8
+		| VEPU_REG_INPUT_SWAP16
+		| VEPU_REG_INPUT_SWAP32;
+	/* Make sure that all registers are written at this point. */
+	vepu_write(vpu, reg, VEPU_REG_DATA_ENDIAN);
+
+	reg = VEPU_REG_AXI_CTRL_BURST_LEN(16);
+	vepu_write_relaxed(vpu, reg, VEPU_REG_AXI_CTRL);
+
+	reg = VEPU_REG_MB_WIDTH(JPEG_MB_WIDTH(ctx->src_fmt.width))
+		| VEPU_REG_MB_HEIGHT(JPEG_MB_HEIGHT(ctx->src_fmt.height))
+		| VEPU_REG_FRAME_TYPE_INTRA
+		| VEPU_REG_ENCODE_FORMAT_JPEG
+		| VEPU_REG_ENCODE_ENABLE;
+
+	/* Kick the watchdog and start encoding */
+	schedule_delayed_work(&vpu->watchdog_work, msecs_to_jiffies(2000));
+	vepu_write(vpu, reg, VEPU_REG_ENCODE_START);
+}

drivers/staging/media/rockchip/vpu/rockchip_vpu.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright 2018 Google LLC.
+ *	Tomasz Figa <tfiga@chromium.org>
+ *
+ * Based on s5p-mfc driver by Samsung Electronics Co., Ltd.
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ */
+
+#ifndef ROCKCHIP_VPU_H_
+#define ROCKCHIP_VPU_H_
+
+#include <linux/platform_device.h>
+#include <linux/videodev2.h>
+#include <linux/wait.h>
+#include <linux/clk.h>
+
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "rockchip_vpu_hw.h"
+
+#define ROCKCHIP_VPU_MAX_CLOCKS		4
+
+#define JPEG_MB_DIM			16
+#define JPEG_MB_WIDTH(w)		DIV_ROUND_UP(w, JPEG_MB_DIM)
+#define JPEG_MB_HEIGHT(h)		DIV_ROUND_UP(h, JPEG_MB_DIM)
+
+struct rockchip_vpu_ctx;
+struct rockchip_vpu_codec_ops;
+
+#define RK_VPU_CODEC_JPEG BIT(0)
+
+/**
+ * struct rockchip_vpu_variant - information about VPU hardware variant
+ *
+ * @enc_offset:			Offset from VPU base to encoder registers.
+ * @enc_fmts:			Encoder formats.
+ * @num_enc_fmts:		Number of encoder formats.
+ * @codec:			Supported codecs
+ * @codec_ops:			Codec ops.
+ * @init:			Initialize hardware.
+ * @vepu_irq:			encoder interrupt handler
+ * @clk_names:			array of clock names
+ * @num_clocks:			number of clocks in the array
+ */
+struct rockchip_vpu_variant {
+	unsigned int enc_offset;
+	const struct rockchip_vpu_fmt *enc_fmts;
+	unsigned int num_enc_fmts;
+	unsigned int codec;
+	const struct rockchip_vpu_codec_ops *codec_ops;
+	int (*init)(struct rockchip_vpu_dev *vpu);
+	irqreturn_t (*vepu_irq)(int irq, void *priv);
+	const char *clk_names[ROCKCHIP_VPU_MAX_CLOCKS];
+	int num_clocks;
+};
+
+/**
+ * enum rockchip_vpu_codec_mode - codec operating mode.
+ * @RK_VPU_MODE_NONE:  No operating mode. Used for RAW video formats.
+ * @RK_VPU_MODE_JPEG_ENC: JPEG encoder.
+ */
+enum rockchip_vpu_codec_mode {
+	RK_VPU_MODE_NONE = -1,
+	RK_VPU_MODE_JPEG_ENC,
+};
+
+/**
+ * struct rockchip_vpu_dev - driver data
+ * @v4l2_dev:		V4L2 device to register video devices for.
+ * @m2m_dev:		mem2mem device associated to this device.
+ * @mdev:		media device associated to this device.
+ * @vfd_enc:		Video device for encoder.
+ * @pdev:		Pointer to VPU platform device.
+ * @dev:		Pointer to device for convenient logging using
+ *			dev_ macros.
+ * @clocks:		Array of clock handles.
+ * @base:		Mapped address of VPU registers.
+ * @enc_base:		Mapped address of VPU encoder register for convenience.
+ * @vpu_mutex:		Mutex to synchronize V4L2 calls.
+ * @irqlock:		Spinlock to synchronize access to data structures
+ *			shared with interrupt handlers.
+ * @variant:		Hardware variant-specific parameters.
+ * @watchdog_work:	Delayed work for hardware timeout handling.
+ */
+struct rockchip_vpu_dev {
+	struct v4l2_device v4l2_dev;
+	struct v4l2_m2m_dev *m2m_dev;
+	struct media_device mdev;
+	struct video_device *vfd_enc;
+	struct platform_device *pdev;
+	struct device *dev;
+	struct clk_bulk_data clocks[ROCKCHIP_VPU_MAX_CLOCKS];
+	void __iomem *base;
+	void __iomem *enc_base;
+
+	struct mutex vpu_mutex;	/* video_device lock */
+	spinlock_t irqlock;
+	const struct rockchip_vpu_variant *variant;
+	struct delayed_work watchdog_work;
+};
+
+/**
+ * struct rockchip_vpu_ctx - Context (instance) private data.
+ *
+ * @dev:		VPU driver data to which the context belongs.
+ * @fh:			V4L2 file handler.
+ *
+ * @sequence_cap:       Sequence counter for capture queue
+ * @sequence_out:       Sequence counter for output queue
+ *
+ * @vpu_src_fmt:	Descriptor of active source format.
+ * @src_fmt:		V4L2 pixel format of active source format.
+ * @vpu_dst_fmt:	Descriptor of active destination format.
+ * @dst_fmt:		V4L2 pixel format of active destination format.
+ *
+ * @ctrl_handler:	Control handler used to register controls.
+ * @jpeg_quality:	User-specified JPEG compression quality.
+ *
+ * @codec_ops:		Set of operations related to codec mode.
+ *
+ * @bounce_dma_addr:	Bounce buffer bus address.
+ * @bounce_buf:		Bounce buffer pointer.
+ * @bounce_size:	Bounce buffer size.
+ */
+struct rockchip_vpu_ctx {
+	struct rockchip_vpu_dev *dev;
+	struct v4l2_fh fh;
+
+	u32 sequence_cap;
+	u32 sequence_out;
+
+	const struct rockchip_vpu_fmt *vpu_src_fmt;
+	struct v4l2_pix_format_mplane src_fmt;
+	const struct rockchip_vpu_fmt *vpu_dst_fmt;
+	struct v4l2_pix_format_mplane dst_fmt;
+
+	struct v4l2_ctrl_handler ctrl_handler;
+	int jpeg_quality;
+
+	const struct rockchip_vpu_codec_ops *codec_ops;
+
+	dma_addr_t bounce_dma_addr;
+	void *bounce_buf;
+	size_t bounce_size;
+};
+
+/**
+ * struct rockchip_vpu_fmt - information about supported video formats.
+ * @name:	Human readable name of the format.
+ * @fourcc:	FourCC code of the format. See V4L2_PIX_FMT_*.
+ * @codec_mode:	Codec mode related to this format. See
+ *		enum rockchip_vpu_codec_mode.
+ * @header_size: Optional header size. Currently used by JPEG encoder.
+ * @max_depth:	Maximum depth, for bitstream formats
+ * @enc_fmt:	Format identifier for encoder registers.
+ * @frmsize:	Supported range of frame sizes (only for bitstream formats).
+ */
+struct rockchip_vpu_fmt {
+	char *name;
+	u32 fourcc;
+	enum rockchip_vpu_codec_mode codec_mode;
+	int header_size;
+	int max_depth;
+	enum rockchip_vpu_enc_fmt enc_fmt;
+	struct v4l2_frmsize_stepwise frmsize;
+};
+
+/* Logging helpers */
+
+/**
+ * debug - Module parameter to control level of debugging messages.
+ *
+ * Level of debugging messages can be controlled by bits of
+ * module parameter called "debug". Meaning of particular
+ * bits is as follows:
+ *
+ * bit 0 - global information: mode, size, init, release
+ * bit 1 - each run start/result information
+ * bit 2 - contents of small controls from userspace
+ * bit 3 - contents of big controls from userspace
+ * bit 4 - detail fmt, ctrl, buffer q/dq information
+ * bit 5 - detail function enter/leave trace information
+ * bit 6 - register write/read information
+ */
+extern int rockchip_vpu_debug;
+
+#define vpu_debug(level, fmt, args...)				\
+	do {							\
+		if (rockchip_vpu_debug & BIT(level))		\
+			pr_info("%s:%d: " fmt,	                \
+				 __func__, __LINE__, ##args);	\
+	} while (0)
+
+#define vpu_err(fmt, args...)					\
+	pr_err("%s:%d: " fmt, __func__, __LINE__, ##args)
+
+/* Structure access helpers. */
+static inline struct rockchip_vpu_ctx *fh_to_ctx(struct v4l2_fh *fh)
+{
+	return container_of(fh, struct rockchip_vpu_ctx, fh);
+}
+
+/* Register accessors. */
+static inline void vepu_write_relaxed(struct rockchip_vpu_dev *vpu,
+				      u32 val, u32 reg)
+{
+	vpu_debug(6, "0x%04x = 0x%08x\n", reg / 4, val);
+	writel_relaxed(val, vpu->enc_base + reg);
+}
+
+static inline void vepu_write(struct rockchip_vpu_dev *vpu, u32 val, u32 reg)
+{
+	vpu_debug(6, "0x%04x = 0x%08x\n", reg / 4, val);
+	writel(val, vpu->enc_base + reg);
+}
+
+static inline u32 vepu_read(struct rockchip_vpu_dev *vpu, u32 reg)
+{
+	u32 val = readl(vpu->enc_base + reg);
+
+	vpu_debug(6, "0x%04x = 0x%08x\n", reg / 4, val);
+	return val;
+}
+
+#endif /* ROCKCHIP_VPU_H_ */

drivers/staging/media/rockchip/vpu/rockchip_vpu_common.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright (C) 2018 Rockchip Electronics Co., Ltd.
+ *	Alpha Lin <Alpha.Lin@rock-chips.com>
+ *	Jeffy Chen <jeffy.chen@rock-chips.com>
+ *
+ * Copyright 2018 Google LLC.
+ *	Tomasz Figa <tfiga@chromium.org>
+ *
+ * Based on s5p-mfc driver by Samsung Electronics Co., Ltd.
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ */
+
+#ifndef ROCKCHIP_VPU_COMMON_H_
+#define ROCKCHIP_VPU_COMMON_H_
+
+#include "rockchip_vpu.h"
+
+extern const struct v4l2_ioctl_ops rockchip_vpu_enc_ioctl_ops;
+extern const struct vb2_ops rockchip_vpu_enc_queue_ops;
+
+void rockchip_vpu_enc_reset_src_fmt(struct rockchip_vpu_dev *vpu,
+				    struct rockchip_vpu_ctx *ctx);
+void rockchip_vpu_enc_reset_dst_fmt(struct rockchip_vpu_dev *vpu,
+				    struct rockchip_vpu_ctx *ctx);
+
+#endif /* ROCKCHIP_VPU_COMMON_H_ */

drivers/staging/media/rockchip/vpu/rockchip_vpu_hw.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Rockchip VPU codec driver
+ *
+ * Copyright 2018 Google LLC.
+ *	Tomasz Figa <tfiga@chromium.org>
+ */
+
+#ifndef ROCKCHIP_VPU_HW_H_
+#define ROCKCHIP_VPU_HW_H_
+
+#include <linux/interrupt.h>
+#include <linux/v4l2-controls.h>
+#include <media/videobuf2-core.h>
+
+struct rockchip_vpu_dev;
+struct rockchip_vpu_ctx;
+struct rockchip_vpu_buf;
+struct rockchip_vpu_variant;
+
+/**
+ * struct rockchip_vpu_codec_ops - codec mode specific operations
+ *
+ * @run:	Start single {en,de)coding job. Called from atomic context
+ *		to indicate that a pair of buffers is ready and the hardware
+ *		should be programmed and started.
+ * @done:	Read back processing results and additional data from hardware.
+ * @reset:	Reset the hardware in case of a timeout.
+ */
+struct rockchip_vpu_codec_ops {
+	void (*run)(struct rockchip_vpu_ctx *ctx);
+	void (*done)(struct rockchip_vpu_ctx *ctx, enum vb2_buffer_state);
+	void (*reset)(struct rockchip_vpu_ctx *ctx);
+};
+
+/**
+ * enum rockchip_vpu_enc_fmt - source format ID for hardware registers.
+ */
+enum rockchip_vpu_enc_fmt {
+	RK3288_VPU_ENC_FMT_YUV420P = 0,
+	RK3288_VPU_ENC_FMT_YUV420SP = 1,
+	RK3288_VPU_ENC_FMT_YUYV422 = 2,
+	RK3288_VPU_ENC_FMT_UYVY422 = 3,
+};
+
+extern const struct rockchip_vpu_variant rk3399_vpu_variant;
+extern const struct rockchip_vpu_variant rk3288_vpu_variant;
+
+void rockchip_vpu_watchdog(struct work_struct *work);
+void rockchip_vpu_run(struct rockchip_vpu_ctx *ctx);
+void rockchip_vpu_irq_done(struct rockchip_vpu_dev *vpu,
+			   unsigned int bytesused,
+			   enum vb2_buffer_state result);
+
+void rk3288_vpu_jpeg_enc_run(struct rockchip_vpu_ctx *ctx);
+void rk3399_vpu_jpeg_enc_run(struct rockchip_vpu_ctx *ctx);
+
+#endif /* ROCKCHIP_VPU_HW_H_ */

drivers/staging/media/rockchip/vpu/rockchip_vpu_jpeg.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) Collabora, Ltd.
+ *
+ * Based on GSPCA and CODA drivers:
+ * Copyright (C) Jean-Francois Moine (http://moinejf.free.fr)
+ * Copyright (C) 2014 Philipp Zabel, Pengutronix
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include "rockchip_vpu_jpeg.h"
+
+#define LUMA_QUANT_OFF		7
+#define CHROMA_QUANT_OFF	72
+#define HEIGHT_OFF		141
+#define WIDTH_OFF		143
+
+#define HUFF_LUMA_DC_OFF	160
+#define HUFF_LUMA_AC_OFF	193
+#define HUFF_CHROMA_DC_OFF	376
+#define HUFF_CHROMA_AC_OFF	409
+
+/* Default tables from JPEG ITU-T.81
+ * (ISO/IEC 10918-1) Annex K.3, I
+ */
+static const unsigned char luma_q_table[] = {
+	0x10, 0x0b, 0x0a, 0x10, 0x7c, 0x8c, 0x97, 0xa1,
+	0x0c, 0x0c, 0x0e, 0x13, 0x7e, 0x9e, 0xa0, 0x9b,
+	0x0e, 0x0d, 0x10, 0x18, 0x8c, 0x9d, 0xa9, 0x9c,
+	0x0e, 0x11, 0x16, 0x1d, 0x97, 0xbb, 0xb4, 0xa2,
+	0x12, 0x16, 0x25, 0x38, 0xa8, 0x6d, 0x67, 0xb1,
+	0x18, 0x23, 0x37, 0x40, 0xb5, 0x68, 0x71, 0xc0,
+	0x31, 0x40, 0x4e, 0x57, 0x67, 0x79, 0x78, 0x65,
+	0x48, 0x5c, 0x5f, 0x62, 0x70, 0x64, 0x67, 0xc7,
+};
+
+static const unsigned char chroma_q_table[] = {
+	0x11, 0x12, 0x18, 0x2f, 0x63, 0x63, 0x63, 0x63,
+	0x12, 0x15, 0x1a, 0x42, 0x63, 0x63, 0x63, 0x63,
+	0x18, 0x1a, 0x38, 0x63, 0x63, 0x63, 0x63, 0x63,
+	0x2f, 0x42, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
+	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
+	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
+	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
+	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63
+};
+
+/* Huffman tables are shared with CODA */
+static const unsigned char luma_dc_table[] = {
+	0x00, 0x01, 0x05, 0x01, 0x01, 0x01, 0x01, 0x01,
+	0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0a, 0x0b,
+};
+
+static const unsigned char chroma_dc_table[] = {
+	0x00, 0x03, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+	0x01, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0a, 0x0b,
+};
+
+static const unsigned char luma_ac_table[] = {
+	0x00, 0x02, 0x01, 0x03, 0x03, 0x02, 0x04, 0x03,
+	0x05, 0x05, 0x04, 0x04, 0x00, 0x00, 0x01, 0x7d,
+	0x01, 0x02, 0x03, 0x00, 0x04, 0x11, 0x05, 0x12,
+	0x21, 0x31, 0x41, 0x06, 0x13, 0x51, 0x61, 0x07,
+	0x22, 0x71, 0x14, 0x32, 0x81, 0x91, 0xa1, 0x08,
+	0x23, 0x42, 0xb1, 0xc1, 0x15, 0x52, 0xd1, 0xf0,
+	0x24, 0x33, 0x62, 0x72, 0x82, 0x09, 0x0a, 0x16,
+	0x17, 0x18, 0x19, 0x1a, 0x25, 0x26, 0x27, 0x28,
+	0x29, 0x2a, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39,
+	0x3a, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49,
+	0x4a, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59,
+	0x5a, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69,
+	0x6a, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79,
+	0x7a, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89,
+	0x8a, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98,
+	0x99, 0x9a, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
+	0xa8, 0xa9, 0xaa, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6,
+	0xb7, 0xb8, 0xb9, 0xba, 0xc2, 0xc3, 0xc4, 0xc5,
+	0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xd2, 0xd3, 0xd4,
+	0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xe1, 0xe2,
+	0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea,
+	0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8,
+	0xf9, 0xfa,
+};
+
+static const unsigned char chroma_ac_table[] = {
+	0x00, 0x02, 0x01, 0x02, 0x04, 0x04, 0x03, 0x04,
+	0x07, 0x05, 0x04, 0x04, 0x00, 0x01, 0x02, 0x77,
+	0x00, 0x01, 0x02, 0x03, 0x11, 0x04, 0x05, 0x21,
+	0x31, 0x06, 0x12, 0x41, 0x51, 0x07, 0x61, 0x71,
+	0x13, 0x22, 0x32, 0x81, 0x08, 0x14, 0x42, 0x91,
+	0xa1, 0xb1, 0xc1, 0x09, 0x23, 0x33, 0x52, 0xf0,
+	0x15, 0x62, 0x72, 0xd1, 0x0a, 0x16, 0x24, 0x34,
+	0xe1, 0x25, 0xf1, 0x17, 0x18, 0x19, 0x1a, 0x26,
+	0x27, 0x28, 0x29, 0x2a, 0x35, 0x36, 0x37, 0x38,
+	0x39, 0x3a, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
+	0x49, 0x4a, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58,
+	0x59, 0x5a, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68,
+	0x69, 0x6a, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+	0x79, 0x7a, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8a, 0x92, 0x93, 0x94, 0x95, 0x96,
+	0x97, 0x98, 0x99, 0x9a, 0xa2, 0xa3, 0xa4, 0xa5,
+	0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xb2, 0xb3, 0xb4,
+	0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xc2, 0xc3,
+	0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xd2,
+	0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda,
+	0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9,
+	0xea, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8,
+	0xf9, 0xfa,
+};
+
+/* For simplicity, we keep a pre-formatted JPEG header,
+ * and we'll use fixed offsets to change the width, height
+ * quantization tables, etc.
+ */
+static const unsigned char rockchip_vpu_jpeg_header[JPEG_HEADER_SIZE] = {
+	/* SOI */
+	0xff, 0xd8,
+
+	/* DQT */
+	0xff, 0xdb, 0x00, 0x84,
+
+	0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	0x01,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* SOF */
+	0xff, 0xc0, 0x00, 0x11, 0x08, 0x00, 0xf0, 0x01,
+	0x40, 0x03, 0x01, 0x22, 0x00, 0x02, 0x11, 0x01,
+	0x03, 0x11, 0x01,
+
+	/* DHT */
+	0xff, 0xc4, 0x00, 0x1f, 0x00,
+
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	/* DHT */
+	0xff, 0xc4, 0x00, 0xb5, 0x10,
+
+	0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* DHT */
+	0xff, 0xc4, 0x00, 0x1f, 0x01,
+
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	/* DHT */
+	0xff, 0xc4, 0x00, 0xb5, 0x11,
+
+	0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* SOS */
+	0xff, 0xda, 0x00, 0x0c, 0x03, 0x01, 0x00, 0x02,
+	0x11, 0x03, 0x11, 0x00, 0x3f, 0x00,
+};
+
+static void
+jpeg_scale_quant_table(unsigned char *q_tab,
+		       const unsigned char *tab, int scale)
+{
+	unsigned int temp;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		temp = DIV_ROUND_CLOSEST((unsigned int)tab[i] * scale, 100);
+		if (temp <= 0)
+			temp = 1;
+		if (temp > 255)
+			temp = 255;
+		q_tab[i] = (unsigned char)temp;
+	}
+}
+
+static void jpeg_set_quality(unsigned char *buffer, int quality)
+{
+	int scale;
+
+	/*
+	 * Non-linear scaling factor:
+	 * [5,50] -> [1000..100], [51,100] -> [98..0]
+	 */
+	if (quality < 50)
+		scale = 5000 / quality;
+	else
+		scale = 200 - 2 * quality;
+
+	jpeg_scale_quant_table(buffer + LUMA_QUANT_OFF,
+			       luma_q_table, scale);
+	jpeg_scale_quant_table(buffer + CHROMA_QUANT_OFF,
+			       chroma_q_table, scale);
+}
+
+unsigned char *
+rockchip_vpu_jpeg_get_qtable(struct rockchip_vpu_jpeg_ctx *ctx, int index)
+{
+	if (index == 0)
+		return ctx->buffer + LUMA_QUANT_OFF;
+	return ctx->buffer + CHROMA_QUANT_OFF;
+}
+
+void rockchip_vpu_jpeg_header_assemble(struct rockchip_vpu_jpeg_ctx *ctx)
+{
+	char *buf = ctx->buffer;
+
+	memcpy(buf, rockchip_vpu_jpeg_header,
+	       sizeof(rockchip_vpu_jpeg_header));
+
+	buf[HEIGHT_OFF + 0] = ctx->height >> 8;
+	buf[HEIGHT_OFF + 1] = ctx->height;
+	buf[WIDTH_OFF + 0] = ctx->width >> 8;
+	buf[WIDTH_OFF + 1] = ctx->width;
+
+	memcpy(buf + HUFF_LUMA_DC_OFF, luma_dc_table, sizeof(luma_dc_table));
+	memcpy(buf + HUFF_LUMA_AC_OFF, luma_ac_table, sizeof(luma_ac_table));
+	memcpy(buf + HUFF_CHROMA_DC_OFF, chroma_dc_table,
+	       sizeof(chroma_dc_table));
+	memcpy(buf + HUFF_CHROMA_AC_OFF, chroma_ac_table,
+	       sizeof(chroma_ac_table));
+
+	jpeg_set_quality(buf, ctx->quality);
+}

drivers/staging/media/rockchip/vpu/rockchip_vpu_jpeg.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#define JPEG_HEADER_SIZE	601
+
+struct rockchip_vpu_jpeg_ctx {
+	int width;
+	int height;
+	int quality;
+	unsigned char *buffer;
+};
+
+unsigned char *
+rockchip_vpu_jpeg_get_qtable(struct rockchip_vpu_jpeg_ctx *ctx, int index);
+void rockchip_vpu_jpeg_header_assemble(struct rockchip_vpu_jpeg_ctx *ctx);