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

@@ -0,0 +1,13 @@
+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

@@ -0,0 +1,10 @@
+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

@@ -0,0 +1,13 @@
+* 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

@@ -0,0 +1,118 @@
+// 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

@@ -0,0 +1,130 @@
+// 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);
+}