[media] rockchip/rga: v4l2 m2m support

Rockchip RGA is a separate 2D raster graphic acceleration unit. It
accelerates 2D graphics operations, such as point/line drawing, image
scaling, rotation, BitBLT, alpha blending and image blur/sharpness

The driver supports various operations from the rendering pipeline.
 - copy
 - fast solid color fill
 - rotation
 - flip
 - alpha blending

The code in rga-hw.c is used to configure regs according to operations
The code in rga-buf.c is used to create private mmu table for RGA.

Signed-off-by: Jacob Chen <jacob-chen@iotwrt.com>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>

6 files changed, 2152 insertions, 0 deletions

diff --git a/drivers/media/platform/rockchip/rga/Makefile b/drivers/media/platform/rockchip/rga/Makefile
new file mode 100644
index 000000000000..92fe25490ccd
--- /dev/null
+++ b/drivers/media/platform/rockchip/rga/Makefile
@@ -0,0 +1,3 @@
+rockchip-rga-objs := rga.o rga-hw.o rga-buf.o
+
+obj-$(CONFIG_VIDEO_ROCKCHIP_RGA) += rockchip-rga.o
diff --git a/drivers/media/platform/rockchip/rga/rga-buf.c b/drivers/media/platform/rockchip/rga/rga-buf.c
new file mode 100644
index 000000000000..49cacc7a48d1
--- /dev/null
+++ b/drivers/media/platform/rockchip/rga/rga-buf.c
@@ -0,0 +1,154 @@
+/*
+ * Copyright (C) 2017 Fuzhou Rockchip Electronics Co.Ltd
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/pm_runtime.h>
+
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-dma-sg.h>
+#include <media/videobuf2-v4l2.h>
+
+#include "rga-hw.h"
+#include "rga.h"
+
+static int
+rga_queue_setup(struct vb2_queue *vq,
+		unsigned int *nbuffers, unsigned int *nplanes,
+		unsigned int sizes[], struct device *alloc_devs[])
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(vq);
+	struct rga_frame *f = rga_get_frame(ctx, vq->type);
+
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	if (*nplanes)
+		return sizes[0] < f->size ? -EINVAL : 0;
+
+	sizes[0] = f->size;
+	*nplanes = 1;
+
+	return 0;
+}
+
+static int rga_buf_prepare(struct vb2_buffer *vb)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rga_frame *f = rga_get_frame(ctx, vb->vb2_queue->type);
+
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	vb2_set_plane_payload(vb, 0, f->size);
+
+	return 0;
+}
+
+static void rga_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
+}
+
+static int rga_buf_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(q);
+	struct rockchip_rga *rga = ctx->rga;
+	int ret, i;
+
+	ret = pm_runtime_get_sync(rga->dev);
+
+	if (!ret)
+		return 0;
+
+	for (i = 0; i < q->num_buffers; ++i) {
+		if (q->bufs[i]->state == VB2_BUF_STATE_ACTIVE) {
+			v4l2_m2m_buf_done(to_vb2_v4l2_buffer(q->bufs[i]),
+					  VB2_BUF_STATE_QUEUED);
+		}
+	}
+
+	return ret;
+}
+
+static void rga_buf_stop_streaming(struct vb2_queue *q)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(q);
+	struct rockchip_rga *rga = ctx->rga;
+	struct vb2_v4l2_buffer *vbuf;
+
+	for (;;) {
+		if (V4L2_TYPE_IS_OUTPUT(q->type))
+			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		else
+			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+		if (!vbuf)
+			break;
+		v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_ERROR);
+	}
+
+	pm_runtime_put(rga->dev);
+}
+
+const struct vb2_ops rga_qops = {
+	.queue_setup = rga_queue_setup,
+	.buf_prepare = rga_buf_prepare,
+	.buf_queue = rga_buf_queue,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.start_streaming = rga_buf_start_streaming,
+	.stop_streaming = rga_buf_stop_streaming,
+};
+
+/* RGA MMU is a 1-Level MMU, so it can't be used through the IOMMU API.
+ * We use it more like a scatter-gather list.
+ */
+void rga_buf_map(struct vb2_buffer *vb)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rockchip_rga *rga = ctx->rga;
+	struct sg_table *sgt;
+	struct scatterlist *sgl;
+	unsigned int *pages;
+	unsigned int address, len, i, p;
+	unsigned int mapped_size = 0;
+
+	if (vb->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		pages = rga->src_mmu_pages;
+	else
+		pages = rga->dst_mmu_pages;
+
+	/* Create local MMU table for RGA */
+	sgt = vb2_plane_cookie(vb, 0);
+
+	for_each_sg(sgt->sgl, sgl, sgt->nents, i) {
+		len = sg_dma_len(sgl) >> PAGE_SHIFT;
+		address = sg_phys(sgl);
+
+		for (p = 0; p < len; p++) {
+			dma_addr_t phys = address + (p << PAGE_SHIFT);
+
+			pages[mapped_size + p] = phys;
+		}
+
+		mapped_size += len;
+	}
+
+	/* sync local MMU table for RGA */
+	dma_sync_single_for_device(rga->dev, virt_to_phys(pages),
+				   8 * PAGE_SIZE, DMA_BIDIRECTIONAL);
+}
diff --git a/drivers/media/platform/rockchip/rga/rga-hw.c b/drivers/media/platform/rockchip/rga/rga-hw.c
new file mode 100644
index 000000000000..0645481c9a5e
--- /dev/null
+++ b/drivers/media/platform/rockchip/rga/rga-hw.c
@@ -0,0 +1,421 @@
+/*
+ * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/pm_runtime.h>
+
+#include "rga-hw.h"
+#include "rga.h"
+
+enum e_rga_start_pos {
+	LT = 0,
+	LB = 1,
+	RT = 2,
+	RB = 3,
+};
+
+struct rga_addr_offset {
+	unsigned int y_off;
+	unsigned int u_off;
+	unsigned int v_off;
+};
+
+struct rga_corners_addr_offset {
+	struct rga_addr_offset left_top;
+	struct rga_addr_offset right_top;
+	struct rga_addr_offset left_bottom;
+	struct rga_addr_offset right_bottom;
+};
+
+static unsigned int rga_get_scaling(unsigned int src, unsigned int dst)
+{
+	/*
+	 * The rga hw scaling factor is a normalized inverse of the
+	 * scaling factor.
+	 * For example: When source width is 100 and destination width is 200
+	 * (scaling of 2x), then the hw factor is NC * 100 / 200.
+	 * The normalization factor (NC) is 2^16 = 0x10000.
+	 */
+
+	return (src > dst) ? ((dst << 16) / src) : ((src << 16) / dst);
+}
+
+static struct rga_corners_addr_offset
+rga_get_addr_offset(struct rga_frame *frm, unsigned int x, unsigned int y,
+		    unsigned int w, unsigned int h)
+{
+	struct rga_corners_addr_offset offsets;
+	struct rga_addr_offset *lt, *lb, *rt, *rb;
+	unsigned int x_div = 0,
+		     y_div = 0, uv_stride = 0, pixel_width = 0, uv_factor = 0;
+
+	lt = &offsets.left_top;
+	lb = &offsets.left_bottom;
+	rt = &offsets.right_top;
+	rb = &offsets.right_bottom;
+
+	x_div = frm->fmt->x_div;
+	y_div = frm->fmt->y_div;
+	uv_factor = frm->fmt->uv_factor;
+	uv_stride = frm->stride / x_div;
+	pixel_width = frm->stride / frm->width;
+
+	lt->y_off = y * frm->stride + x * pixel_width;
+	lt->u_off =
+		frm->width * frm->height + (y / y_div) * uv_stride + x / x_div;
+	lt->v_off = lt->u_off + frm->width * frm->height / uv_factor;
+
+	lb->y_off = lt->y_off + (h - 1) * frm->stride;
+	lb->u_off = lt->u_off + (h / y_div - 1) * uv_stride;
+	lb->v_off = lt->v_off + (h / y_div - 1) * uv_stride;
+
+	rt->y_off = lt->y_off + (w - 1) * pixel_width;
+	rt->u_off = lt->u_off + w / x_div - 1;
+	rt->v_off = lt->v_off + w / x_div - 1;
+
+	rb->y_off = lb->y_off + (w - 1) * pixel_width;
+	rb->u_off = lb->u_off + w / x_div - 1;
+	rb->v_off = lb->v_off + w / x_div - 1;
+
+	return offsets;
+}
+
+static struct rga_addr_offset *rga_lookup_draw_pos(struct
+		rga_corners_addr_offset
+		* offsets, u32 rotate_mode,
+		u32 mirr_mode)
+{
+	static enum e_rga_start_pos rot_mir_point_matrix[4][4] = {
+		{
+			LT, RT, LB, RB,
+		},
+		{
+			RT, LT, RB, LB,
+		},
+		{
+			RB, LB, RT, LT,
+		},
+		{
+			LB, RB, LT, RT,
+		},
+	};
+
+	if (!offsets)
+		return NULL;
+
+	switch (rot_mir_point_matrix[rotate_mode][mirr_mode]) {
+	case LT:
+		return &offsets->left_top;
+	case LB:
+		return &offsets->left_bottom;
+	case RT:
+		return &offsets->right_top;
+	case RB:
+		return &offsets->right_bottom;
+	}
+
+	return NULL;
+}
+
+static void rga_cmd_set_src_addr(struct rga_ctx *ctx, void *mmu_pages)
+{
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA_MMU_SRC_BASE - RGA_MODE_BASE_REG;
+	dest[reg >> 2] = virt_to_phys(mmu_pages) >> 4;
+
+	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
+	dest[reg >> 2] |= 0x7;
+}
+
+static void rga_cmd_set_src1_addr(struct rga_ctx *ctx, void *mmu_pages)
+{
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA_MMU_SRC1_BASE - RGA_MODE_BASE_REG;
+	dest[reg >> 2] = virt_to_phys(mmu_pages) >> 4;
+
+	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
+	dest[reg >> 2] |= 0x7 << 4;
+}
+
+static void rga_cmd_set_dst_addr(struct rga_ctx *ctx, void *mmu_pages)
+{
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA_MMU_DST_BASE - RGA_MODE_BASE_REG;
+	dest[reg >> 2] = virt_to_phys(mmu_pages) >> 4;
+
+	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
+	dest[reg >> 2] |= 0x7 << 8;
+}
+
+static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
+{
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	unsigned int scale_dst_w, scale_dst_h;
+	unsigned int src_h, src_w, src_x, src_y, dst_h, dst_w, dst_x, dst_y;
+	union rga_src_info src_info;
+	union rga_dst_info dst_info;
+	union rga_src_x_factor x_factor;
+	union rga_src_y_factor y_factor;
+	union rga_src_vir_info src_vir_info;
+	union rga_src_act_info src_act_info;
+	union rga_dst_vir_info dst_vir_info;
+	union rga_dst_act_info dst_act_info;
+
+	struct rga_addr_offset *dst_offset;
+	struct rga_corners_addr_offset offsets;
+	struct rga_corners_addr_offset src_offsets;
+
+	src_h = ctx->in.crop.height;
+	src_w = ctx->in.crop.width;
+	src_x = ctx->in.crop.left;
+	src_y = ctx->in.crop.top;
+	dst_h = ctx->out.crop.height;
+	dst_w = ctx->out.crop.width;
+	dst_x = ctx->out.crop.left;
+	dst_y = ctx->out.crop.top;
+
+	src_info.val = dest[(RGA_SRC_INFO - RGA_MODE_BASE_REG) >> 2];
+	dst_info.val = dest[(RGA_DST_INFO - RGA_MODE_BASE_REG) >> 2];
+	x_factor.val = dest[(RGA_SRC_X_FACTOR - RGA_MODE_BASE_REG) >> 2];
+	y_factor.val = dest[(RGA_SRC_Y_FACTOR - RGA_MODE_BASE_REG) >> 2];
+	src_vir_info.val = dest[(RGA_SRC_VIR_INFO - RGA_MODE_BASE_REG) >> 2];
+	src_act_info.val = dest[(RGA_SRC_ACT_INFO - RGA_MODE_BASE_REG) >> 2];
+	dst_vir_info.val = dest[(RGA_DST_VIR_INFO - RGA_MODE_BASE_REG) >> 2];
+	dst_act_info.val = dest[(RGA_DST_ACT_INFO - RGA_MODE_BASE_REG) >> 2];
+
+	src_info.data.format = ctx->in.fmt->hw_format;
+	src_info.data.swap = ctx->in.fmt->color_swap;
+	dst_info.data.format = ctx->out.fmt->hw_format;
+	dst_info.data.swap = ctx->out.fmt->color_swap;
+
+	if (ctx->in.fmt->hw_format >= RGA_COLOR_FMT_YUV422SP) {
+		if (ctx->out.fmt->hw_format < RGA_COLOR_FMT_YUV422SP) {
+			switch (ctx->in.colorspace) {
+			case V4L2_COLORSPACE_REC709:
+				src_info.data.csc_mode =
+					RGA_SRC_CSC_MODE_BT709_R0;
+				break;
+			default:
+				src_info.data.csc_mode =
+					RGA_SRC_CSC_MODE_BT601_R0;
+				break;
+			}
+		}
+	}
+
+	if (ctx->out.fmt->hw_format >= RGA_COLOR_FMT_YUV422SP) {
+		switch (ctx->out.colorspace) {
+		case V4L2_COLORSPACE_REC709:
+			dst_info.data.csc_mode = RGA_SRC_CSC_MODE_BT709_R0;
+			break;
+		default:
+			dst_info.data.csc_mode = RGA_DST_CSC_MODE_BT601_R0;
+			break;
+		}
+	}
+
+	if (ctx->vflip)
+		src_info.data.mir_mode |= RGA_SRC_MIRR_MODE_X;
+
+	if (ctx->hflip)
+		src_info.data.mir_mode |= RGA_SRC_MIRR_MODE_Y;
+
+	switch (ctx->rotate) {
+	case 90:
+		src_info.data.rot_mode = RGA_SRC_ROT_MODE_90_DEGREE;
+		break;
+	case 180:
+		src_info.data.rot_mode = RGA_SRC_ROT_MODE_180_DEGREE;
+		break;
+	case 270:
+		src_info.data.rot_mode = RGA_SRC_ROT_MODE_270_DEGREE;
+		break;
+	default:
+		src_info.data.rot_mode = RGA_SRC_ROT_MODE_0_DEGREE;
+		break;
+	}
+
+	/*
+	 * Cacluate the up/down scaling mode/factor.
+	 *
+	 * RGA used to scale the picture first, and then rotate second,
+	 * so we need to swap the w/h when rotate degree is 90/270.
+	 */
+	if (src_info.data.rot_mode == RGA_SRC_ROT_MODE_90_DEGREE ||
+	    src_info.data.rot_mode == RGA_SRC_ROT_MODE_270_DEGREE) {
+		if (rga->version.major == 0 || rga->version.minor == 0) {
+			if (dst_w == src_h)
+				src_h -= 8;
+			if (abs(src_w - dst_h) < 16)
+				src_w -= 16;
+		}
+
+		scale_dst_h = dst_w;
+		scale_dst_w = dst_h;
+	} else {
+		scale_dst_w = dst_w;
+		scale_dst_h = dst_h;
+	}
+
+	if (src_w == scale_dst_w) {
+		src_info.data.hscl_mode = RGA_SRC_HSCL_MODE_NO;
+		x_factor.val = 0;
+	} else if (src_w > scale_dst_w) {
+		src_info.data.hscl_mode = RGA_SRC_HSCL_MODE_DOWN;
+		x_factor.data.down_scale_factor =
+			rga_get_scaling(src_w, scale_dst_w) + 1;
+	} else {
+		src_info.data.hscl_mode = RGA_SRC_HSCL_MODE_UP;
+		x_factor.data.up_scale_factor =
+			rga_get_scaling(src_w - 1, scale_dst_w - 1);
+	}
+
+	if (src_h == scale_dst_h) {
+		src_info.data.vscl_mode = RGA_SRC_VSCL_MODE_NO;
+		y_factor.val = 0;
+	} else if (src_h > scale_dst_h) {
+		src_info.data.vscl_mode = RGA_SRC_VSCL_MODE_DOWN;
+		y_factor.data.down_scale_factor =
+			rga_get_scaling(src_h, scale_dst_h) + 1;
+	} else {
+		src_info.data.vscl_mode = RGA_SRC_VSCL_MODE_UP;
+		y_factor.data.up_scale_factor =
+			rga_get_scaling(src_h - 1, scale_dst_h - 1);
+	}
+
+	/*
+	 * Cacluate the framebuffer virtual strides and active size,
+	 * note that the step of vir_stride / vir_width is 4 byte words
+	 */
+	src_vir_info.data.vir_stride = ctx->in.stride >> 2;
+	src_vir_info.data.vir_width = ctx->in.stride >> 2;
+
+	src_act_info.data.act_height = src_h - 1;
+	src_act_info.data.act_width = src_w - 1;
+
+	dst_vir_info.data.vir_stride = ctx->out.stride >> 2;
+	dst_act_info.data.act_height = dst_h - 1;
+	dst_act_info.data.act_width = dst_w - 1;
+
+	/*
+	 * Cacluate the source framebuffer base address with offset pixel.
+	 */
+	src_offsets = rga_get_addr_offset(&ctx->in, src_x, src_y,
+					  src_w, src_h);
+
+	/*
+	 * Configure the dest framebuffer base address with pixel offset.
+	 */
+	offsets = rga_get_addr_offset(&ctx->out, dst_x, dst_y, dst_w, dst_h);
+	dst_offset = rga_lookup_draw_pos(&offsets, src_info.data.rot_mode,
+					 src_info.data.mir_mode);
+
+	dest[(RGA_SRC_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		src_offsets.left_top.y_off;
+	dest[(RGA_SRC_CB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		src_offsets.left_top.u_off;
+	dest[(RGA_SRC_CR_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		src_offsets.left_top.v_off;
+
+	dest[(RGA_SRC_X_FACTOR - RGA_MODE_BASE_REG) >> 2] = x_factor.val;
+	dest[(RGA_SRC_Y_FACTOR - RGA_MODE_BASE_REG) >> 2] = y_factor.val;
+	dest[(RGA_SRC_VIR_INFO - RGA_MODE_BASE_REG) >> 2] = src_vir_info.val;
+	dest[(RGA_SRC_ACT_INFO - RGA_MODE_BASE_REG) >> 2] = src_act_info.val;
+
+	dest[(RGA_SRC_INFO - RGA_MODE_BASE_REG) >> 2] = src_info.val;
+
+	dest[(RGA_DST_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		dst_offset->y_off;
+	dest[(RGA_DST_CB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		dst_offset->u_off;
+	dest[(RGA_DST_CR_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		dst_offset->v_off;
+
+	dest[(RGA_DST_VIR_INFO - RGA_MODE_BASE_REG) >> 2] = dst_vir_info.val;
+	dest[(RGA_DST_ACT_INFO - RGA_MODE_BASE_REG) >> 2] = dst_act_info.val;
+
+	dest[(RGA_DST_INFO - RGA_MODE_BASE_REG) >> 2] = dst_info.val;
+}
+
+static void rga_cmd_set_mode(struct rga_ctx *ctx)
+{
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	union rga_mode_ctrl mode;
+	union rga_alpha_ctrl0 alpha_ctrl0;
+	union rga_alpha_ctrl1 alpha_ctrl1;
+
+	mode.val = 0;
+	alpha_ctrl0.val = 0;
+	alpha_ctrl1.val = 0;
+
+	mode.data.gradient_sat = 1;
+	mode.data.render = RGA_MODE_RENDER_BITBLT;
+	mode.data.bitblt = RGA_MODE_BITBLT_MODE_SRC_TO_DST;
+
+	/* disable alpha blending */
+	dest[(RGA_ALPHA_CTRL0 - RGA_MODE_BASE_REG) >> 2] = alpha_ctrl0.val;
+	dest[(RGA_ALPHA_CTRL1 - RGA_MODE_BASE_REG) >> 2] = alpha_ctrl1.val;
+
+	dest[(RGA_MODE_CTRL - RGA_MODE_BASE_REG) >> 2] = mode.val;
+}
+
+void rga_cmd_set(struct rga_ctx *ctx)
+{
+	struct rockchip_rga *rga = ctx->rga;
+
+	memset(rga->cmdbuf_virt, 0, RGA_CMDBUF_SIZE * 4);
+
+	rga_cmd_set_src_addr(ctx, rga->src_mmu_pages);
+	/*
+	 * Due to hardware bug,
+	 * src1 mmu also should be configured when using alpha blending.
+	 */
+	rga_cmd_set_src1_addr(ctx, rga->dst_mmu_pages);
+
+	rga_cmd_set_dst_addr(ctx, rga->dst_mmu_pages);
+	rga_cmd_set_mode(ctx);
+
+	rga_cmd_set_trans_info(ctx);
+
+	rga_write(rga, RGA_CMD_BASE, rga->cmdbuf_phy);
+
+	/* sync CMD buf for RGA */
+	dma_sync_single_for_device(rga->dev, rga->cmdbuf_phy,
+		PAGE_SIZE, DMA_BIDIRECTIONAL);
+}
+
+void rga_hw_start(struct rockchip_rga *rga)
+{
+	struct rga_ctx *ctx = rga->curr;
+
+	rga_cmd_set(ctx);
+
+	rga_write(rga, RGA_SYS_CTRL, 0x00);
+
+	rga_write(rga, RGA_SYS_CTRL, 0x22);
+
+	rga_write(rga, RGA_INT, 0x600);
+
+	rga_write(rga, RGA_CMD_CTRL, 0x1);
+}
diff --git a/drivers/media/platform/rockchip/rga/rga-hw.h b/drivers/media/platform/rockchip/rga/rga-hw.h
new file mode 100644
index 000000000000..ca3c204abe42
--- /dev/null
+++ b/drivers/media/platform/rockchip/rga/rga-hw.h
@@ -0,0 +1,437 @@
+/*
+ * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef __RGA_HW_H__
+#define __RGA_HW_H__
+
+#define RGA_CMDBUF_SIZE 0x20
+
+/* Hardware limits */
+#define MAX_WIDTH 8192
+#define MAX_HEIGHT 8192
+
+#define MIN_WIDTH 34
+#define MIN_HEIGHT 34
+
+#define DEFAULT_WIDTH 100
+#define DEFAULT_HEIGHT 100
+
+#define RGA_TIMEOUT 500
+
+/* Registers address */
+#define RGA_SYS_CTRL 0x0000
+#define RGA_CMD_CTRL 0x0004
+#define RGA_CMD_BASE 0x0008
+#define RGA_INT 0x0010
+#define RGA_MMU_CTRL0 0x0014
+#define RGA_VERSION_INFO 0x0028
+
+#define RGA_MODE_BASE_REG 0x0100
+#define RGA_MODE_MAX_REG 0x017C
+
+#define RGA_MODE_CTRL 0x0100
+#define RGA_SRC_INFO 0x0104
+#define RGA_SRC_Y_RGB_BASE_ADDR 0x0108
+#define RGA_SRC_CB_BASE_ADDR 0x010c
+#define RGA_SRC_CR_BASE_ADDR 0x0110
+#define RGA_SRC1_RGB_BASE_ADDR 0x0114
+#define RGA_SRC_VIR_INFO 0x0118
+#define RGA_SRC_ACT_INFO 0x011c
+#define RGA_SRC_X_FACTOR 0x0120
+#define RGA_SRC_Y_FACTOR 0x0124
+#define RGA_SRC_BG_COLOR 0x0128
+#define RGA_SRC_FG_COLOR 0x012c
+#define RGA_SRC_TR_COLOR0 0x0130
+#define RGA_SRC_TR_COLOR1 0x0134
+
+#define RGA_DST_INFO 0x0138
+#define RGA_DST_Y_RGB_BASE_ADDR 0x013c
+#define RGA_DST_CB_BASE_ADDR 0x0140
+#define RGA_DST_CR_BASE_ADDR 0x0144
+#define RGA_DST_VIR_INFO 0x0148
+#define RGA_DST_ACT_INFO 0x014c
+
+#define RGA_ALPHA_CTRL0 0x0150
+#define RGA_ALPHA_CTRL1 0x0154
+#define RGA_FADING_CTRL 0x0158
+#define RGA_PAT_CON 0x015c
+#define RGA_ROP_CON0 0x0160
+#define RGA_ROP_CON1 0x0164
+#define RGA_MASK_BASE 0x0168
+
+#define RGA_MMU_CTRL1 0x016C
+#define RGA_MMU_SRC_BASE 0x0170
+#define RGA_MMU_SRC1_BASE 0x0174
+#define RGA_MMU_DST_BASE 0x0178
+
+/* Registers value */
+#define RGA_MODE_RENDER_BITBLT 0
+#define RGA_MODE_RENDER_COLOR_PALETTE 1
+#define RGA_MODE_RENDER_RECTANGLE_FILL 2
+#define RGA_MODE_RENDER_UPDATE_PALETTE_LUT_RAM 3
+
+#define RGA_MODE_BITBLT_MODE_SRC_TO_DST 0
+#define RGA_MODE_BITBLT_MODE_SRC_SRC1_TO_DST 1
+
+#define RGA_MODE_CF_ROP4_SOLID 0
+#define RGA_MODE_CF_ROP4_PATTERN 1
+
+#define RGA_COLOR_FMT_ABGR8888 0
+#define RGA_COLOR_FMT_XBGR8888 1
+#define RGA_COLOR_FMT_RGB888 2
+#define RGA_COLOR_FMT_BGR565 4
+#define RGA_COLOR_FMT_ABGR1555 5
+#define RGA_COLOR_FMT_ABGR4444 6
+#define RGA_COLOR_FMT_YUV422SP 8
+#define RGA_COLOR_FMT_YUV422P 9
+#define RGA_COLOR_FMT_YUV420SP 10
+#define RGA_COLOR_FMT_YUV420P 11
+/* SRC_COLOR Palette */
+#define RGA_COLOR_FMT_CP_1BPP 12
+#define RGA_COLOR_FMT_CP_2BPP 13
+#define RGA_COLOR_FMT_CP_4BPP 14
+#define RGA_COLOR_FMT_CP_8BPP 15
+#define RGA_COLOR_FMT_MASK 15
+
+#define RGA_COLOR_NONE_SWAP 0
+#define RGA_COLOR_RB_SWAP 1
+#define RGA_COLOR_ALPHA_SWAP 2
+#define RGA_COLOR_UV_SWAP 4
+
+#define RGA_SRC_CSC_MODE_BYPASS 0
+#define RGA_SRC_CSC_MODE_BT601_R0 1
+#define RGA_SRC_CSC_MODE_BT601_R1 2
+#define RGA_SRC_CSC_MODE_BT709_R0 3
+#define RGA_SRC_CSC_MODE_BT709_R1 4
+
+#define RGA_SRC_ROT_MODE_0_DEGREE 0
+#define RGA_SRC_ROT_MODE_90_DEGREE 1
+#define RGA_SRC_ROT_MODE_180_DEGREE 2
+#define RGA_SRC_ROT_MODE_270_DEGREE 3
+
+#define RGA_SRC_MIRR_MODE_NO 0
+#define RGA_SRC_MIRR_MODE_X 1
+#define RGA_SRC_MIRR_MODE_Y 2
+#define RGA_SRC_MIRR_MODE_X_Y 3
+
+#define RGA_SRC_HSCL_MODE_NO 0
+#define RGA_SRC_HSCL_MODE_DOWN 1
+#define RGA_SRC_HSCL_MODE_UP 2
+
+#define RGA_SRC_VSCL_MODE_NO 0
+#define RGA_SRC_VSCL_MODE_DOWN 1
+#define RGA_SRC_VSCL_MODE_UP 2
+
+#define RGA_SRC_TRANS_ENABLE_R 1
+#define RGA_SRC_TRANS_ENABLE_G 2
+#define RGA_SRC_TRANS_ENABLE_B 4
+#define RGA_SRC_TRANS_ENABLE_A 8
+
+#define RGA_SRC_BIC_COE_SELEC_CATROM 0
+#define RGA_SRC_BIC_COE_SELEC_MITCHELL 1
+#define RGA_SRC_BIC_COE_SELEC_HERMITE 2
+#define RGA_SRC_BIC_COE_SELEC_BSPLINE 3
+
+#define RGA_DST_DITHER_MODE_888_TO_666 0
+#define RGA_DST_DITHER_MODE_888_TO_565 1
+#define RGA_DST_DITHER_MODE_888_TO_555 2
+#define RGA_DST_DITHER_MODE_888_TO_444 3
+
+#define RGA_DST_CSC_MODE_BYPASS 0
+#define RGA_DST_CSC_MODE_BT601_R0 1
+#define RGA_DST_CSC_MODE_BT601_R1 2
+#define RGA_DST_CSC_MODE_BT709_R0 3
+
+#define RGA_ALPHA_ROP_MODE_2 0
+#define RGA_ALPHA_ROP_MODE_3 1
+#define RGA_ALPHA_ROP_MODE_4 2
+
+#define RGA_ALPHA_SELECT_ALPHA 0
+#define RGA_ALPHA_SELECT_ROP 1
+
+#define RGA_ALPHA_MASK_BIG_ENDIAN 0
+#define RGA_ALPHA_MASK_LITTLE_ENDIAN 1
+
+#define RGA_ALPHA_NORMAL 0
+#define RGA_ALPHA_REVERSE 1
+
+#define RGA_ALPHA_BLEND_GLOBAL 0
+#define RGA_ALPHA_BLEND_NORMAL 1
+#define RGA_ALPHA_BLEND_MULTIPLY 2
+
+#define RGA_ALPHA_CAL_CUT 0
+#define RGA_ALPHA_CAL_NORMAL 1
+
+#define RGA_ALPHA_FACTOR_ZERO 0
+#define RGA_ALPHA_FACTOR_ONE 1
+#define RGA_ALPHA_FACTOR_OTHER 2
+#define RGA_ALPHA_FACTOR_OTHER_REVERSE 3
+#define RGA_ALPHA_FACTOR_SELF 4
+
+#define RGA_ALPHA_COLOR_NORMAL 0
+#define RGA_ALPHA_COLOR_MULTIPLY_CAL 1
+
+/* Registers union */
+union rga_mode_ctrl {
+	unsigned int val;
+	struct {
+		/* [0:2] */
+		unsigned int render:3;
+		/* [3:6] */
+		unsigned int bitblt:1;
+		unsigned int cf_rop4_pat:1;
+		unsigned int alpha_zero_key:1;
+		unsigned int gradient_sat:1;
+		/* [7:31] */
+		unsigned int reserved:25;
+	} data;
+};
+
+union rga_src_info {
+	unsigned int val;
+	struct {
+		/* [0:3] */
+		unsigned int format:4;
+		/* [4:7] */
+		unsigned int swap:3;
+		unsigned int cp_endian:1;
+		/* [8:17] */
+		unsigned int csc_mode:2;
+		unsigned int rot_mode:2;
+		unsigned int mir_mode:2;
+		unsigned int hscl_mode:2;
+		unsigned int vscl_mode:2;
+		/* [18:22] */
+		unsigned int trans_mode:1;
+		unsigned int trans_enable:4;
+		/* [23:25] */
+		unsigned int dither_up_en:1;
+		unsigned int bic_coe_sel:2;
+		/* [26:31] */
+		unsigned int reserved:6;
+	} data;
+};
+
+union rga_src_vir_info {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int vir_width:15;
+		unsigned int reserved:1;
+		/* [16:25] */
+		unsigned int vir_stride:10;
+		/* [26:31] */
+		unsigned int reserved1:6;
+	} data;
+};
+
+union rga_src_act_info {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int act_width:13;
+		unsigned int reserved:3;
+		/* [16:31] */
+		unsigned int act_height:13;
+		unsigned int reserved1:3;
+	} data;
+};
+
+union rga_src_x_factor {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int down_scale_factor:16;
+		/* [16:31] */
+		unsigned int up_scale_factor:16;
+	} data;
+};
+
+union rga_src_y_factor {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int down_scale_factor:16;
+		/* [16:31] */
+		unsigned int up_scale_factor:16;
+	} data;
+};
+
+/* Alpha / Red / Green / Blue */
+union rga_src_cp_gr_color {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int gradient_x:16;
+		/* [16:31] */
+		unsigned int gradient_y:16;
+	} data;
+};
+
+union rga_src_transparency_color0 {
+	unsigned int val;
+	struct {
+		/* [0:7] */
+		unsigned int trans_rmin:8;
+		/* [8:15] */
+		unsigned int trans_gmin:8;
+		/* [16:23] */
+		unsigned int trans_bmin:8;
+		/* [24:31] */
+		unsigned int trans_amin:8;
+	} data;
+};
+
+union rga_src_transparency_color1 {
+	unsigned int val;
+	struct {
+		/* [0:7] */
+		unsigned int trans_rmax:8;
+		/* [8:15] */
+		unsigned int trans_gmax:8;
+		/* [16:23] */
+		unsigned int trans_bmax:8;
+		/* [24:31] */
+		unsigned int trans_amax:8;
+	} data;
+};
+
+union rga_dst_info {
+	unsigned int val;
+	struct {
+		/* [0:3] */
+		unsigned int format:4;
+		/* [4:6] */
+		unsigned int swap:3;
+		/* [7:9] */
+		unsigned int src1_format:3;
+		/* [10:11] */
+		unsigned int src1_swap:2;
+		/* [12:15] */
+		unsigned int dither_up_en:1;
+		unsigned int dither_down_en:1;
+		unsigned int dither_down_mode:2;
+		/* [16:18] */
+		unsigned int csc_mode:2;
+		unsigned int csc_clip:1;
+		/* [19:31] */
+		unsigned int reserved:13;
+	} data;
+};
+
+union rga_dst_vir_info {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int vir_stride:15;
+		unsigned int reserved:1;
+		/* [16:31] */
+		unsigned int src1_vir_stride:15;
+		unsigned int reserved1:1;
+	} data;
+};
+
+union rga_dst_act_info {
+	unsigned int val;
+	struct {
+		/* [0:15] */
+		unsigned int act_width:12;
+		unsigned int reserved:4;
+		/* [16:31] */
+		unsigned int act_height:12;
+		unsigned int reserved1:4;
+	} data;
+};
+
+union rga_alpha_ctrl0 {
+	unsigned int val;
+	struct {
+		/* [0:3] */
+		unsigned int rop_en:1;
+		unsigned int rop_select:1;
+		unsigned int rop_mode:2;
+		/* [4:11] */
+		unsigned int src_fading_val:8;
+		/* [12:20] */
+		unsigned int dst_fading_val:8;
+		unsigned int mask_endian:1;
+		/* [21:31] */
+		unsigned int reserved:11;
+	} data;
+};
+
+union rga_alpha_ctrl1 {
+	unsigned int val;
+	struct {
+		/* [0:1] */
+		unsigned int dst_color_m0:1;
+		unsigned int src_color_m0:1;
+		/* [2:7] */
+		unsigned int dst_factor_m0:3;
+		unsigned int src_factor_m0:3;
+		/* [8:9] */
+		unsigned int dst_alpha_cal_m0:1;
+		unsigned int src_alpha_cal_m0:1;
+		/* [10:13] */
+		unsigned int dst_blend_m0:2;
+		unsigned int src_blend_m0:2;
+		/* [14:15] */
+		unsigned int dst_alpha_m0:1;
+		unsigned int src_alpha_m0:1;
+		/* [16:21] */
+		unsigned int dst_factor_m1:3;
+		unsigned int src_factor_m1:3;
+		/* [22:23] */
+		unsigned int dst_alpha_cal_m1:1;
+		unsigned int src_alpha_cal_m1:1;
+		/* [24:27] */
+		unsigned int dst_blend_m1:2;
+		unsigned int src_blend_m1:2;
+		/* [28:29] */
+		unsigned int dst_alpha_m1:1;
+		unsigned int src_alpha_m1:1;
+		/* [30:31] */
+		unsigned int reserved:2;
+	} data;
+};
+
+union rga_fading_ctrl {
+	unsigned int val;
+	struct {
+		/* [0:7] */
+		unsigned int fading_offset_r:8;
+		/* [8:15] */
+		unsigned int fading_offset_g:8;
+		/* [16:23] */
+		unsigned int fading_offset_b:8;
+		/* [24:31] */
+		unsigned int fading_en:1;
+		unsigned int reserved:7;
+	} data;
+};
+
+union rga_pat_con {
+	unsigned int val;
+	struct {
+		/* [0:7] */
+		unsigned int width:8;
+		/* [8:15] */
+		unsigned int height:8;
+		/* [16:23] */
+		unsigned int offset_x:8;
+		/* [24:31] */
+		unsigned int offset_y:8;
+	} data;
+};
+
+#endif
diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
new file mode 100644
index 000000000000..2cf3bb29a2b3
--- /dev/null
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -0,0 +1,1012 @@
+/*
+ * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+
+#include <linux/platform_device.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-dma-sg.h>
+#include <media/videobuf2-v4l2.h>
+
+#include "rga-hw.h"
+#include "rga.h"
+
+static int debug;
+module_param(debug, int, 0644);
+
+static void job_abort(void *prv)
+{
+	struct rga_ctx *ctx = prv;
+	struct rockchip_rga *rga = ctx->rga;
+
+	if (!rga->curr)	/* No job currently running */
+		return;
+
+	wait_event_timeout(rga->irq_queue,
+			   !rga->curr, msecs_to_jiffies(RGA_TIMEOUT));
+}
+
+static void device_run(void *prv)
+{
+	struct rga_ctx *ctx = prv;
+	struct rockchip_rga *rga = ctx->rga;
+	struct vb2_buffer *src, *dst;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rga->ctrl_lock, flags);
+
+	rga->curr = ctx;
+
+	src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+
+	rga_buf_map(src);
+	rga_buf_map(dst);
+
+	rga_hw_start(rga);
+
+	spin_unlock_irqrestore(&rga->ctrl_lock, flags);
+}
+
+static irqreturn_t rga_isr(int irq, void *prv)
+{
+	struct rockchip_rga *rga = prv;
+	int intr;
+
+	intr = rga_read(rga, RGA_INT) & 0xf;
+
+	rga_mod(rga, RGA_INT, intr << 4, 0xf << 4);
+
+	if (intr & 0x04) {
+		struct vb2_v4l2_buffer *src, *dst;
+		struct rga_ctx *ctx = rga->curr;
+
+		WARN_ON(!ctx);
+
+		rga->curr = NULL;
+
+		src = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		dst = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+
+		WARN_ON(!src);
+		WARN_ON(!dst);
+
+