Resguardo inicial

linux-7.2.3/drivers/media/platform/rockchip/rga/Kconfig

@@ -0,0 +1,15 @@
+config VIDEO_ROCKCHIP_RGA
+	tristate "Rockchip Raster 2d Graphic Acceleration Unit"
+	depends on V4L_MEM2MEM_DRIVERS
+	depends on VIDEO_DEV
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	select VIDEOBUF2_DMA_CONTIG
+	select VIDEOBUF2_DMA_SG
+	select V4L2_MEM2MEM_DEV
+	help
+	  This is a v4l2 driver for Rockchip SOC RGA 2d graphics accelerator.
+	  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.
+
+	  To compile this driver as a module choose m here.

linux-7.2.3/drivers/media/platform/rockchip/rga/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+rockchip-rga-objs := rga.o rga-hw.o rga3-hw.o rga-buf.o
+
+obj-$(CONFIG_VIDEO_ROCKCHIP_RGA) += rockchip-rga.o

linux-7.2.3/drivers/media/platform/rockchip/rga/rga-buf.c

@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ */
+
+#include <linux/pm_runtime.h>
+#include <linux/scatterlist.h>
+
+#include <media/v4l2-common.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-dma-contig.h>
+#include <media/videobuf2-v4l2.h>
+
+#include "rga.h"
+
+static ssize_t fill_descriptors(struct rga_dma_desc *desc, size_t max_desc,
+				struct sg_table *sgt)
+{
+	struct sg_dma_page_iter iter;
+	struct rga_dma_desc *tmp = desc;
+	size_t n_desc = 0;
+	dma_addr_t addr;
+
+	for_each_sgtable_dma_page(sgt, &iter, 0) {
+		if (n_desc > max_desc)
+			return -EINVAL;
+		addr = sg_page_iter_dma_address(&iter);
+		tmp->addr = lower_32_bits(addr);
+		tmp++;
+		n_desc++;
+	}
+
+	return n_desc;
+}
+
+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);
+	const struct v4l2_pix_format_mplane *pix_fmt;
+	int i;
+
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	pix_fmt = &f->pix;
+
+	if (*nplanes) {
+		if (*nplanes != pix_fmt->num_planes)
+			return -EINVAL;
+
+		for (i = 0; i < pix_fmt->num_planes; i++)
+			if (sizes[i] < pix_fmt->plane_fmt[i].sizeimage)
+				return -EINVAL;
+
+		return 0;
+	}
+
+	*nplanes = pix_fmt->num_planes;
+
+	for (i = 0; i < pix_fmt->num_planes; i++)
+		sizes[i] = pix_fmt->plane_fmt[i].sizeimage;
+
+	return 0;
+}
+
+static int rga_buf_init(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_vb_buffer *rbuf = vb_to_rga(vbuf);
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rockchip_rga *rga = ctx->rga;
+	struct rga_frame *f = rga_get_frame(ctx, vb->vb2_queue->type);
+	size_t n_desc = 0;
+	u32 size = 0;
+	u8 i;
+
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	if (!rga_has_internal_iommu(rga))
+		return 0;
+
+	for (i = 0; i < f->pix.num_planes; i++)
+		size += f->pix.plane_fmt[i].sizeimage;
+	n_desc = DIV_ROUND_UP(size, PAGE_SIZE);
+
+	rbuf->n_desc = n_desc;
+	rbuf->dma_desc = dma_alloc_coherent(rga->dev,
+					    rbuf->n_desc * sizeof(*rbuf->dma_desc),
+					    &rbuf->dma_desc_pa, GFP_KERNEL);
+	if (!rbuf->dma_desc)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int get_plane_offset(struct rga_frame *f,
+			    const struct v4l2_format_info *info,
+			    int plane)
+{
+	u32 stride = f->pix.plane_fmt[0].bytesperline;
+
+	if (plane == 0)
+		return 0;
+	if (plane == 1)
+		return stride * f->pix.height;
+	if (plane == 2)
+		return stride * f->pix.height +
+		       (stride * f->pix.height / info->hdiv / info->vdiv);
+
+	return -EINVAL;
+}
+
+static int rga_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_vb_buffer *rbuf = vb_to_rga(vbuf);
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rga_frame *f = rga_get_frame(ctx, vb->vb2_queue->type);
+	ssize_t n_desc = 0;
+	size_t curr_desc = 0;
+	int i;
+	const struct v4l2_format_info *info;
+	dma_addr_t dma_addrs[VIDEO_MAX_PLANES];
+
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	if (V4L2_TYPE_IS_OUTPUT(vb->vb2_queue->type)) {
+		if (vbuf->field == V4L2_FIELD_ANY)
+			vbuf->field = V4L2_FIELD_NONE;
+		if (vbuf->field != V4L2_FIELD_NONE)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < vb->num_planes; i++) {
+		vb2_set_plane_payload(vb, i, f->pix.plane_fmt[i].sizeimage);
+
+		if (rga_has_internal_iommu(ctx->rga)) {
+			/* Create local MMU table for RGA */
+			n_desc = fill_descriptors(&rbuf->dma_desc[curr_desc],
+						  rbuf->n_desc - curr_desc,
+						  vb2_dma_sg_plane_desc(vb, i));
+			if (n_desc < 0) {
+				v4l2_err(&ctx->rga->v4l2_dev,
+					 "Failed to map video buffer to RGA\n");
+				return n_desc;
+			}
+			dma_addrs[i] = curr_desc << PAGE_SHIFT;
+			curr_desc += n_desc;
+		} else {
+			dma_addrs[i] = vb2_dma_contig_plane_dma_addr(vb, i);
+		}
+	}
+
+	/* Fill the remaining planes */
+	info = v4l2_format_info(f->pix.pixelformat);
+	for (i = info->mem_planes; i < info->comp_planes; i++)
+		dma_addrs[i] = dma_addrs[0] + get_plane_offset(f, info, i);
+
+	rbuf->dma_addrs.y_addr = dma_addrs[0];
+	rbuf->dma_addrs.u_addr = dma_addrs[1];
+	rbuf->dma_addrs.v_addr = dma_addrs[2];
+
+	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 void rga_buf_cleanup(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_vb_buffer *rbuf = vb_to_rga(vbuf);
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rockchip_rga *rga = ctx->rga;
+
+	if (!rga_has_internal_iommu(rga))
+		return;
+
+	dma_free_coherent(rga->dev, rbuf->n_desc * sizeof(*rbuf->dma_desc),
+			  rbuf->dma_desc, rbuf->dma_desc_pa);
+}
+
+static void rga_buf_return_buffers(struct vb2_queue *q,
+				   enum vb2_buffer_state state)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(q);
+	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, state);
+	}
+}
+
+static int rga_buf_prepare_streaming(struct vb2_queue *q)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(q);
+	const struct rga_hw *hw = ctx->rga->hw;
+	int ret;
+
+	/* It's safe to check the streaming state of the other queue,
+	 * as the streamon ioctl's can't race due to the lock set in
+	 * the queue_init function.
+	 */
+	if ((V4L2_TYPE_IS_OUTPUT(q->type) &&
+	     vb2_is_streaming(v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx))) ||
+	    (V4L2_TYPE_IS_CAPTURE(q->type) &&
+	     vb2_is_streaming(v4l2_m2m_get_src_vq(ctx->fh.m2m_ctx)))) {
+		/*
+		 * As the other side is already streaming,
+		 * check that the max scaling factor isn't exceeded.
+		 */
+		ret = rga_check_scaling(hw, &ctx->in.crop, &ctx->out.crop,
+					ctx->rotate);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+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;
+
+	ret = pm_runtime_resume_and_get(rga->dev);
+	if (ret < 0) {
+		rga_buf_return_buffers(q, VB2_BUF_STATE_QUEUED);
+		return ret;
+	}
+
+	if (V4L2_TYPE_IS_OUTPUT(q->type))
+		ctx->osequence = 0;
+	else
+		ctx->csequence = 0;
+
+	return 0;
+}
+
+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;
+
+	rga_buf_return_buffers(q, VB2_BUF_STATE_ERROR);
+	pm_runtime_put(rga->dev);
+}
+
+const struct vb2_ops rga_qops = {
+	.queue_setup = rga_queue_setup,
+	.buf_init = rga_buf_init,
+	.buf_prepare = rga_buf_prepare,
+	.buf_queue = rga_buf_queue,
+	.buf_cleanup = rga_buf_cleanup,
+	.prepare_streaming = rga_buf_prepare_streaming,
+	.start_streaming = rga_buf_start_streaming,
+	.stop_streaming = rga_buf_stop_streaming,
+};

linux-7.2.3/drivers/media/platform/rockchip/rga/rga-hw.c

@@ -0,0 +1,615 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) Rockchip Electronics Co., Ltd.
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ */
+
+#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_corners_addrs {
+	struct rga_addrs left_top;
+	struct rga_addrs right_top;
+	struct rga_addrs left_bottom;
+	struct rga_addrs 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_addrs
+rga_get_corner_addrs(struct rga_frame *frm, struct rga_addrs *addrs,
+		     unsigned int x, unsigned int y, unsigned int w, unsigned int h)
+{
+	struct rga_corners_addrs corner_addrs;
+	struct rga_addrs *lt, *lb, *rt, *rb;
+	const struct v4l2_format_info *format_info;
+	unsigned int x_div = 0,
+		     y_div = 0, y_stride = 0, uv_stride = 0, pixel_width = 0;
+
+	lt = &corner_addrs.left_top;
+	lb = &corner_addrs.left_bottom;
+	rt = &corner_addrs.right_top;
+	rb = &corner_addrs.right_bottom;
+
+	format_info = v4l2_format_info(frm->pix.pixelformat);
+	/* x_div is only used for the u/v planes.
+	 * When the format doesn't have these, use 1 to avoid a division by zero.
+	 */
+	if (format_info->bpp[1])
+		x_div = format_info->hdiv * format_info->bpp_div[1] /
+			format_info->bpp[1];
+	else
+		x_div = 1;
+	y_div = format_info->vdiv;
+	y_stride = frm->pix.plane_fmt[0].bytesperline;
+	uv_stride = y_stride / x_div;
+	pixel_width = y_stride / frm->pix.width;
+
+	lt->y_addr = addrs->y_addr + y * y_stride + x * pixel_width;
+	lt->u_addr = addrs->u_addr + (y / y_div) * uv_stride + x / x_div;
+	lt->v_addr = addrs->v_addr + (y / y_div) * uv_stride + x / x_div;
+
+	lb->y_addr = lt->y_addr + (h - 1) * y_stride;
+	lb->u_addr = lt->u_addr + (h / y_div - 1) * uv_stride;
+	lb->v_addr = lt->v_addr + (h / y_div - 1) * uv_stride;
+
+	rt->y_addr = lt->y_addr + (w - 1) * pixel_width;
+	rt->u_addr = lt->u_addr + w / x_div - 1;
+	rt->v_addr = lt->v_addr + w / x_div - 1;
+
+	rb->y_addr = lb->y_addr + (w - 1) * pixel_width;
+	rb->u_addr = lb->u_addr + w / x_div - 1;
+	rb->v_addr = lb->v_addr + w / x_div - 1;
+
+	return corner_addrs;
+}
+
+static struct rga_addrs *rga_lookup_draw_pos(struct rga_corners_addrs *corner_addrs,
+					     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 (!corner_addrs)
+		return NULL;
+
+	switch (rot_mir_point_matrix[rotate_mode][mirr_mode]) {
+	case LT:
+		return &corner_addrs->left_top;
+	case LB:
+		return &corner_addrs->left_bottom;
+	case RT:
+		return &corner_addrs->right_top;
+	case RB:
+		return &corner_addrs->right_bottom;
+	}
+
+	return NULL;
+}
+
+static void rga_cmd_set_src_addr(struct rga_ctx *ctx, dma_addr_t dma_addr)
+{
+	u32 *dest = ctx->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA_MMU_SRC_BASE - RGA_MODE_BASE_REG;
+	dest[reg >> 2] = dma_addr >> 4;
+
+	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
+	dest[reg >> 2] |= 0x7;
+}
+
+static void rga_cmd_set_src1_addr(struct rga_ctx *ctx, dma_addr_t dma_addr)
+{
+	u32 *dest = ctx->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA_MMU_SRC1_BASE - RGA_MODE_BASE_REG;
+	dest[reg >> 2] = dma_addr >> 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, dma_addr_t dma_addr)
+{
+	u32 *dest = ctx->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA_MMU_DST_BASE - RGA_MODE_BASE_REG;
+	dest[reg >> 2] = dma_addr >> 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 = ctx->cmdbuf_virt;
+	unsigned int scale_dst_w, scale_dst_h;
+	unsigned int src_h, src_w, dst_h, dst_w;
+	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;
+	u32 in_stride, out_stride;
+	struct rga_fmt *in_fmt = ctx->in.fmt;
+	struct rga_fmt *out_fmt = ctx->out.fmt;
+
+	src_h = ctx->in.crop.height;
+	src_w = ctx->in.crop.width;
+	dst_h = ctx->out.crop.height;
+	dst_w = ctx->out.crop.width;
+
+	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 = in_fmt->hw_format;
+	src_info.data.swap = in_fmt->color_swap;
+	dst_info.data.format = out_fmt->hw_format;
+	dst_info.data.swap = out_fmt->color_swap;
+
+	/*
+	 * CSC mode must only be set when the colorspace families differ between
+	 * input and output. It must remain unset (zeroed) if both are the same.
+	 */
+
+	if (RGA_COLOR_FMT_IS_YUV(in_fmt->hw_format) &&
+	    RGA_COLOR_FMT_IS_RGB(out_fmt->hw_format)) {
+		switch (ctx->in.pix.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 (RGA_COLOR_FMT_IS_RGB(in_fmt->hw_format) &&
+	    RGA_COLOR_FMT_IS_YUV(out_fmt->hw_format)) {
+		switch (ctx->out.pix.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;
+	}
+
+	/*
+	 * Calculate 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);
+	}
+
+	/*
+	 * Calculate the framebuffer virtual strides and active size,
+	 * note that the step of vir_stride / vir_width is 4 byte words
+	 */
+	in_stride = ctx->in.pix.plane_fmt[0].bytesperline;
+	src_vir_info.data.vir_stride = in_stride >> 2;
+	src_vir_info.data.vir_width = in_stride >> 2;
+
+	src_act_info.data.act_height = src_h - 1;
+	src_act_info.data.act_width = src_w - 1;
+
+	out_stride = ctx->out.pix.plane_fmt[0].bytesperline;
+	dst_vir_info.data.vir_stride = out_stride >> 2;
+	dst_act_info.data.act_height = dst_h - 1;
+	dst_act_info.data.act_width = dst_w - 1;
+
+	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_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_src_info(struct rga_ctx *ctx,
+				 struct rga_addrs *addrs)
+{
+	struct rga_corners_addrs src_corner_addrs;
+	u32 *dest = ctx->cmdbuf_virt;
+	unsigned int src_h, src_w, src_x, src_y;
+
+	src_h = ctx->in.crop.height;
+	src_w = ctx->in.crop.width;
+	src_x = ctx->in.crop.left;
+	src_y = ctx->in.crop.top;
+
+	/*
+	 * Calculate the source framebuffer base address with offset pixel.
+	 */
+	src_corner_addrs = rga_get_corner_addrs(&ctx->in, addrs,
+						src_x, src_y, src_w, src_h);
+
+	dest[(RGA_SRC_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		src_corner_addrs.left_top.y_addr;
+	dest[(RGA_SRC_CB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		src_corner_addrs.left_top.u_addr;
+	dest[(RGA_SRC_CR_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		src_corner_addrs.left_top.v_addr;
+}
+
+static void rga_cmd_set_dst_info(struct rga_ctx *ctx,
+				 struct rga_addrs *addrs)
+{
+	struct rga_addrs *dst_addrs;
+	struct rga_corners_addrs corner_addrs;
+	u32 *dest = ctx->cmdbuf_virt;
+	unsigned int dst_h, dst_w, dst_x, dst_y;
+	unsigned int mir_mode = 0;
+	unsigned int rot_mode = 0;
+
+	dst_h = ctx->out.crop.height;
+	dst_w = ctx->out.crop.width;
+	dst_x = ctx->out.crop.left;
+	dst_y = ctx->out.crop.top;
+
+	if (ctx->vflip)
+		mir_mode |= RGA_SRC_MIRR_MODE_X;
+	if (ctx->hflip)
+		mir_mode |= RGA_SRC_MIRR_MODE_Y;
+
+	switch (ctx->rotate) {
+	case 90:
+		rot_mode = RGA_SRC_ROT_MODE_90_DEGREE;
+		break;
+	case 180:
+		rot_mode = RGA_SRC_ROT_MODE_180_DEGREE;
+		break;
+	case 270:
+		rot_mode = RGA_SRC_ROT_MODE_270_DEGREE;
+		break;
+	default:
+		rot_mode = RGA_SRC_ROT_MODE_0_DEGREE;
+		break;
+	}
+
+	/*
+	 * Configure the dest framebuffer base address with pixel offset.
+	 */
+	corner_addrs = rga_get_corner_addrs(&ctx->out, addrs, dst_x, dst_y, dst_w, dst_h);
+	dst_addrs = rga_lookup_draw_pos(&corner_addrs, rot_mode, mir_mode);
+
+	dest[(RGA_DST_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		dst_addrs->y_addr;
+	dest[(RGA_DST_CB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		dst_addrs->u_addr;
+	dest[(RGA_DST_CR_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
+		dst_addrs->v_addr;
+}
+
+static void rga_cmd_set_mode(struct rga_ctx *ctx)
+{
+	u32 *dest = ctx->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;
+}
+
+static void rga_cmd_set(struct rga_ctx *ctx,
+			struct rga_vb_buffer *src, struct rga_vb_buffer *dst)
+{
+	struct rockchip_rga *rga = ctx->rga;
+
+	rga_cmd_set_src_addr(ctx, src->dma_desc_pa);
+	/*
+	 * Due to hardware bug,
+	 * src1 mmu also should be configured when using alpha blending.
+	 */
+	rga_cmd_set_src1_addr(ctx, dst->dma_desc_pa);
+
+	rga_cmd_set_dst_addr(ctx, dst->dma_desc_pa);
+
+	rga_cmd_set_src_info(ctx, &src->dma_addrs);
+	rga_cmd_set_dst_info(ctx, &dst->dma_addrs);
+
+	rga_write(rga, RGA_CMD_BASE, ctx->cmdbuf_phy);
+
+	/* sync CMD buf for RGA */
+	dma_sync_single_for_device(rga->dev, ctx->cmdbuf_phy,
+				   PAGE_SIZE, DMA_BIDIRECTIONAL);
+}
+
+static void rga_hw_setup_cmdbuf(struct rga_ctx *ctx)
+{
+	memset(ctx->cmdbuf_virt, 0, RGA_CMDBUF_SIZE);
+
+	rga_cmd_set_mode(ctx);
+	rga_cmd_set_trans_info(ctx);
+}
+
+static void rga_hw_start(struct rockchip_rga *rga,
+			 struct rga_vb_buffer *src,  struct rga_vb_buffer *dst)
+{
+	struct rga_ctx *ctx = rga->curr;
+
+	rga_cmd_set(ctx, src, dst);
+
+	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);
+}
+
+static bool rga_handle_irq(struct rockchip_rga *rga)
+{
+	int intr;
+
+	intr = rga_read(rga, RGA_INT) & 0xf;
+
+	rga_mod(rga, RGA_INT, intr << 4, 0xf << 4);
+
+	return intr & RGA_INT_COMMAND_FINISHED;
+}
+
+static void rga_get_version(struct rockchip_rga *rga)
+{
+	rga->version.major = (rga_read(rga, RGA_VERSION_INFO) >> 24) & 0xFF;
+	rga->version.minor = (rga_read(rga, RGA_VERSION_INFO) >> 20) & 0x0F;
+}
+
+static struct rga_fmt formats[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_ARGB32,
+		.color_swap = RGA_COLOR_ALPHA_SWAP,
+		.hw_format = RGA_COLOR_FMT_ABGR8888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_ABGR32,
+		.color_swap = RGA_COLOR_RB_SWAP,
+		.hw_format = RGA_COLOR_FMT_ABGR8888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_XBGR32,
+		.color_swap = RGA_COLOR_RB_SWAP,
+		.hw_format = RGA_COLOR_FMT_XBGR8888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_RGB24,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_RGB888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_BGR24,
+		.color_swap = RGA_COLOR_RB_SWAP,
+		.hw_format = RGA_COLOR_FMT_RGB888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_ARGB444,
+		.color_swap = RGA_COLOR_RB_SWAP,
+		.hw_format = RGA_COLOR_FMT_ABGR4444,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_ARGB555,
+		.color_swap = RGA_COLOR_RB_SWAP,
+		.hw_format = RGA_COLOR_FMT_ABGR1555,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_RGB565,
+		.color_swap = RGA_COLOR_RB_SWAP,
+		.hw_format = RGA_COLOR_FMT_BGR565,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV21,
+		.color_swap = RGA_COLOR_UV_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV420SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV61,
+		.color_swap = RGA_COLOR_UV_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV422SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV12,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV420SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV420SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV16,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV422SP,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YUV420,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV420P,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YUV422P,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV422P,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YVU420,
+		.color_swap = RGA_COLOR_UV_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV420P,
+	},
+};
+
+static void *rga_adjust_and_map_format(struct rga_ctx *ctx,
+				       struct v4l2_pix_format_mplane *format,
+				       bool is_output)
+{
+	unsigned int i;
+
+	if (!format)
+		return &formats[0];
+
+	for (i = 0; i < ARRAY_SIZE(formats); i++) {
+		if (formats[i].fourcc == format->pixelformat)
+			return &formats[i];
+	}
+
+	format->pixelformat = formats[0].fourcc;
+	return &formats[0];
+}
+
+static int rga_enum_format(struct v4l2_fmtdesc *f)
+{
+	if (f->index >= ARRAY_SIZE(formats))
+		return -EINVAL;
+
+	f->pixelformat = formats[f->index].fourcc;
+	return 0;
+}
+
+const struct rga_hw rga2_hw = {
+	.card_type = "rga2",
+	.has_internal_iommu = true,
+	.cmdbuf_size = RGA_CMDBUF_SIZE,
+	.min_width = MIN_WIDTH,
+	.max_width = MAX_WIDTH,
+	.min_height = MIN_HEIGHT,
+	.max_height = MAX_HEIGHT,
+	.max_scaling_factor = MAX_SCALING_FACTOR,
+	.stride_alignment = 4,
+	.features = RGA_FEATURE_FLIP
+		  | RGA_FEATURE_ROTATE
+		  | RGA_FEATURE_BG_COLOR,
+
+	.setup_cmdbuf = rga_hw_setup_cmdbuf,
+	.start = rga_hw_start,
+	.handle_irq = rga_handle_irq,
+	.get_version = rga_get_version,
+	.adjust_and_map_format = rga_adjust_and_map_format,
+	.enum_format = rga_enum_format,
+};

linux-7.2.3/drivers/media/platform/rockchip/rga/rga-hw.h

@@ -0,0 +1,442 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) Rockchip Electronics Co., Ltd.
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ */
+#ifndef __RGA_HW_H__
+#define __RGA_HW_H__
+
+#include <linux/types.h>
+
+#define RGA_CMDBUF_SIZE 0x80
+
+/* Hardware limits */
+#define MAX_WIDTH 8192
+#define MAX_HEIGHT 8192
+
+#define MIN_WIDTH 34
+#define MIN_HEIGHT 34
+#define MAX_SCALING_FACTOR 16
+
+#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_FMT_IS_YUV(fmt) \
+	(((fmt) >= RGA_COLOR_FMT_YUV422SP) && ((fmt) < RGA_COLOR_FMT_CP_1BPP))
+#define RGA_COLOR_FMT_IS_RGB(fmt) \
+	((fmt) < RGA_COLOR_FMT_YUV422SP)
+
+#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
+
+#define RGA_INT_COMMAND_FINISHED 4
+
+/* 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;
+};
+
+struct rga_fmt {
+	u32 fourcc;
+	u8 color_swap;
+	u8 hw_format;
+};
+
+#endif

linux-7.2.3/drivers/media/platform/rockchip/rga/rga.c

@@ -0,0 +1,939 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) Rockchip Electronics Co., Ltd.
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ */
+
+#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-dma-contig.h>
+#include <media/videobuf2-v4l2.h>
+
+#include "rga.h"
+
+static int debug;
+module_param(debug, int, 0644);
+
+static void device_run(void *prv)
+{
+	struct rga_ctx *ctx = prv;
+	struct rockchip_rga *rga = ctx->rga;
+	struct vb2_v4l2_buffer *src, *dst;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rga->ctrl_lock, flags);
+	if (ctx->cmdbuf_dirty) {
+		ctx->cmdbuf_dirty = false;
+		rga->hw->setup_cmdbuf(ctx);
+	}
+	spin_unlock_irqrestore(&rga->ctrl_lock, flags);
+
+	rga->curr = ctx;
+
+	src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	src->sequence = ctx->osequence++;
+
+	dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+
+	rga->hw->start(rga, vb_to_rga(src), vb_to_rga(dst));
+}
+
+static irqreturn_t rga_isr(int irq, void *prv)
+{
+	struct rockchip_rga *rga = prv;
+
+	if (rga->hw->handle_irq(rga)) {
+		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);
+
+		v4l2_m2m_buf_copy_metadata(src, dst);
+
+		dst->sequence = ctx->csequence++;
+
+		v4l2_m2m_buf_done(src, VB2_BUF_STATE_DONE);
+		v4l2_m2m_buf_done(dst, VB2_BUF_STATE_DONE);
+		v4l2_m2m_job_finish(rga->m2m_dev, ctx->fh.m2m_ctx);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static const struct v4l2_m2m_ops rga_m2m_ops = {
+	.device_run = device_run,
+};
+
+static int
+queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq)
+{
+	struct rga_ctx *ctx = priv;
+	int ret;
+
+	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
+	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
+	src_vq->drv_priv = ctx;
+	src_vq->ops = &rga_qops;
+	if (rga_has_internal_iommu(ctx->rga))
+		src_vq->mem_ops = &vb2_dma_sg_memops;
+	else
+		src_vq->mem_ops = &vb2_dma_contig_memops;
+	src_vq->gfp_flags = __GFP_DMA32;
+	src_vq->buf_struct_size = sizeof(struct rga_vb_buffer);
+	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->lock = &ctx->rga->mutex;
+	src_vq->dev = ctx->rga->v4l2_dev.dev;
+
+	ret = vb2_queue_init(src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
+	dst_vq->drv_priv = ctx;
+	dst_vq->ops = &rga_qops;
+	if (rga_has_internal_iommu(ctx->rga))
+		dst_vq->mem_ops = &vb2_dma_sg_memops;
+	else
+		dst_vq->mem_ops = &vb2_dma_contig_memops;
+	dst_vq->gfp_flags = __GFP_DMA32;
+	dst_vq->buf_struct_size = sizeof(struct rga_vb_buffer);
+	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->lock = &ctx->rga->mutex;
+	dst_vq->dev = ctx->rga->v4l2_dev.dev;
+
+	return vb2_queue_init(dst_vq);
+}
+
+static int rga_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct rga_ctx *ctx = container_of(ctrl->handler, struct rga_ctx,
+					   ctrl_handler);
+	const struct rga_hw *hw = ctx->rga->hw;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&ctx->rga->ctrl_lock, flags);
+	switch (ctrl->id) {
+	case V4L2_CID_HFLIP:
+		ctx->hflip = ctrl->val;
+		break;
+	case V4L2_CID_VFLIP:
+		ctx->vflip = ctrl->val;
+		break;
+	case V4L2_CID_ROTATE:
+		if (vb2_is_streaming(v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx)) &&
+		    vb2_is_streaming(v4l2_m2m_get_src_vq(ctx->fh.m2m_ctx))) {
+			ret = rga_check_scaling(hw, &ctx->in.crop,
+						&ctx->out.crop, ctrl->val);
+			if (ret < 0)
+				goto s_ctrl_done;
+		}
+		ctx->rotate = ctrl->val;
+		break;
+	case V4L2_CID_BG_COLOR:
+		ctx->fill_color = ctrl->val;
+		break;
+	}
+	ctx->cmdbuf_dirty = true;
+
+s_ctrl_done:
+	spin_unlock_irqrestore(&ctx->rga->ctrl_lock, flags);
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops rga_ctrl_ops = {
+	.s_ctrl = rga_s_ctrl,
+};
+
+static int rga_setup_ctrls(struct rga_ctx *ctx)
+{
+	struct rockchip_rga *rga = ctx->rga;
+
+	v4l2_ctrl_handler_init(&ctx->ctrl_handler, 4);
+
+	if (rga->hw->features & RGA_FEATURE_FLIP) {
+		v4l2_ctrl_new_std(&ctx->ctrl_handler, &rga_ctrl_ops,
+				  V4L2_CID_HFLIP, 0, 1, 1, 0);
+
+		v4l2_ctrl_new_std(&ctx->ctrl_handler, &rga_ctrl_ops,
+				  V4L2_CID_VFLIP, 0, 1, 1, 0);
+	}
+
+	if (rga->hw->features & RGA_FEATURE_ROTATE)
+		v4l2_ctrl_new_std(&ctx->ctrl_handler, &rga_ctrl_ops,
+				  V4L2_CID_ROTATE, 0, 270, 90, 0);
+
+	if (rga->hw->features & RGA_FEATURE_BG_COLOR)
+		v4l2_ctrl_new_std(&ctx->ctrl_handler, &rga_ctrl_ops,
+				  V4L2_CID_BG_COLOR, 0, 0xffffffff, 1, 0);
+
+	if (ctx->ctrl_handler.error) {
+		int err = ctx->ctrl_handler.error;
+
+		v4l2_err(&rga->v4l2_dev, "%s failed\n", __func__);
+		v4l2_ctrl_handler_free(&ctx->ctrl_handler);
+		return err;
+	}
+
+	return 0;
+}
+
+static bool check_scaling_factor(const struct rga_hw *hw, u32 src_size,
+				 u32 dst_size)
+{
+	if (src_size < dst_size)
+		return src_size * hw->max_scaling_factor >= dst_size;
+	else
+		return dst_size * hw->max_scaling_factor >= src_size;
+}
+
+int rga_check_scaling(const struct rga_hw *hw, const struct v4l2_rect *crop_in,
+		      const struct v4l2_rect *crop_out, u32 rotate)
+{
+	u32 scaled_width;
+	u32 scaled_height;
+
+	if (rotate == 90 || rotate == 270) {
+		scaled_width = crop_out->height;
+		scaled_height = crop_out->width;
+	} else {
+		scaled_width = crop_out->width;
+		scaled_height = crop_out->height;
+	}
+
+	if (!check_scaling_factor(hw, crop_in->width, scaled_width))
+		return -EINVAL;
+
+	if (!check_scaling_factor(hw, crop_in->height, scaled_height))
+		return -EINVAL;
+
+	return 0;
+}
+
+struct rga_frame *rga_get_frame(struct rga_ctx *ctx, enum v4l2_buf_type type)
+{
+	if (V4L2_TYPE_IS_OUTPUT(type))
+		return &ctx->in;
+	if (V4L2_TYPE_IS_CAPTURE(type))
+		return &ctx->out;
+	return ERR_PTR(-EINVAL);
+}
+
+static int rga_open(struct file *file)
+{
+	struct rockchip_rga *rga = video_drvdata(file);
+	struct rga_ctx *ctx = NULL;
+	int ret = 0;
+	u32 def_width = clamp(DEFAULT_WIDTH, rga->hw->min_width, rga->hw->max_width);
+	u32 def_height = clamp(DEFAULT_HEIGHT, rga->hw->min_height, rga->hw->max_height);
+	struct rga_frame def_frame = {
+		.crop.left = 0,
+		.crop.top = 0,
+		.crop.width = def_width,
+		.crop.height = def_height,
+	};
+
+	ctx = kzalloc_obj(*ctx);
+	if (!ctx)
+		return -ENOMEM;
+
+	/* Create CMD buffer */
+	ctx->cmdbuf_virt = dma_alloc_attrs(rga->dev, rga->hw->cmdbuf_size,
+					   &ctx->cmdbuf_phy, GFP_KERNEL,
+					   DMA_ATTR_WRITE_COMBINE);
+	if (!ctx->cmdbuf_virt) {
+		ret = -ENOMEM;
+		goto rel_ctx;
+	}
+	ctx->cmdbuf_dirty = true;
+
+	ctx->rga = rga;
+	/* Set default formats */
+	ctx->in = def_frame;
+	ctx->out = def_frame;
+
+	ctx->in.fmt = rga->hw->adjust_and_map_format(ctx, &ctx->in.pix, true);
+	v4l2_fill_pixfmt_mp_aligned(&ctx->in.pix, ctx->in.pix.pixelformat,
+				    def_width, def_height, rga->hw->stride_alignment);
+	ctx->out.fmt =
+		rga->hw->adjust_and_map_format(ctx, &ctx->out.pix, false);
+	v4l2_fill_pixfmt_mp_aligned(&ctx->out.pix, ctx->out.pix.pixelformat,
+				    def_width, def_height, rga->hw->stride_alignment);
+
+	if (mutex_lock_interruptible(&rga->mutex)) {
+		ret = -ERESTARTSYS;
+		goto rel_cmdbuf;
+	}
+	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(rga->m2m_dev, ctx, &queue_init);
+	if (IS_ERR(ctx->fh.m2m_ctx)) {
+		ret = PTR_ERR(ctx->fh.m2m_ctx);
+		goto unlock_mutex;
+	}
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	v4l2_fh_add(&ctx->fh, file);
+
+	rga_setup_ctrls(ctx);
+
+	/* Write the default values to the ctx struct */
+	v4l2_ctrl_handler_setup(&ctx->ctrl_handler);
+
+	ctx->fh.ctrl_handler = &ctx->ctrl_handler;
+	mutex_unlock(&rga->mutex);
+
+	return 0;
+
+unlock_mutex:
+	mutex_unlock(&rga->mutex);
+rel_cmdbuf:
+	dma_free_attrs(rga->dev, rga->hw->cmdbuf_size, ctx->cmdbuf_virt,
+		       ctx->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE);
+rel_ctx:
+	kfree(ctx);
+	return ret;
+}
+
+static int rga_release(struct file *file)
+{
+	struct rga_ctx *ctx = file_to_rga_ctx(file);
+	struct rockchip_rga *rga = ctx->rga;
+
+	mutex_lock(&rga->mutex);
+
+	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
+
+	v4l2_ctrl_handler_free(&ctx->ctrl_handler);
+	v4l2_fh_del(&ctx->fh, file);
+	v4l2_fh_exit(&ctx->fh);
+
+	dma_free_attrs(rga->dev, rga->hw->cmdbuf_size, ctx->cmdbuf_virt,
+		       ctx->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE);
+
+	kfree(ctx);
+
+	mutex_unlock(&rga->mutex);
+
+	return 0;
+}
+
+static const struct v4l2_file_operations rga_fops = {
+	.owner = THIS_MODULE,
+	.open = rga_open,
+	.release = rga_release,
+	.poll = v4l2_m2m_fop_poll,
+	.unlocked_ioctl = video_ioctl2,
+	.mmap = v4l2_m2m_fop_mmap,
+};
+
+static int
+vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *cap)
+{
+	struct rockchip_rga *rga = video_drvdata(file);
+
+	strscpy(cap->driver, RGA_NAME, sizeof(cap->driver));
+	strscpy(cap->card, rga->hw->card_type, sizeof(cap->card));
+	strscpy(cap->bus_info, "platform:rga", sizeof(cap->bus_info));
+
+	return 0;
+}
+
+static int vidioc_enum_fmt(struct file *file, void *priv, struct v4l2_fmtdesc *f)
+{
+	struct rockchip_rga *rga = video_drvdata(file);
+	int ret;
+
+	ret = rga->hw->enum_format(f);
+	if (ret != 0)
+		return ret;
+
+	if (f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE &&
+	    f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
+		return 0;
+
+	/* allow changing the quantization and xfer func for YUV formats */
+	if (v4l2_is_format_yuv(v4l2_format_info(f->pixelformat)))
+		f->flags |= V4L2_FMT_FLAG_CSC_QUANTIZATION |
+			    V4L2_FMT_FLAG_CSC_YCBCR_ENC;
+
+	return 0;
+}
+
+static int vidioc_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &f->fmt.pix_mp;
+	struct rga_ctx *ctx = file_to_rga_ctx(file);
+	struct rga_frame *frm;
+
+	frm = rga_get_frame(ctx, f->type);
+	if (IS_ERR(frm))
+		return PTR_ERR(frm);
+
+	*pix_fmt = frm->pix;
+	pix_fmt->field = V4L2_FIELD_NONE;
+
+	return 0;
+}
+
+static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &f->fmt.pix_mp;
+	struct rga_ctx *ctx = file_to_rga_ctx(file);
+	const struct rga_hw *hw = ctx->rga->hw;
+	struct v4l2_frmsize_stepwise frmsize = {
+		.min_width = hw->min_width,
+		.max_width = hw->max_width,
+		.min_height = hw->min_height,
+		.max_height = hw->max_height,
+		.step_width = 1,
+		.step_height = 1,
+	};
+
+	if (v4l2_is_format_yuv(v4l2_format_info(pix_fmt->pixelformat))) {
+		frmsize.step_width = 2;
+		frmsize.step_height = 2;
+	}
+
+	if (V4L2_TYPE_IS_CAPTURE(f->type)) {
+		const struct rga_frame *frm;
+
+		frm = rga_get_frame(ctx, f->type);
+		if (IS_ERR(frm))
+			return PTR_ERR(frm);
+
+		if (!(pix_fmt->flags & V4L2_PIX_FMT_FLAG_SET_CSC)) {
+			pix_fmt->quantization = frm->pix.quantization;
+			pix_fmt->ycbcr_enc = frm->pix.ycbcr_enc;
+		}
+		/* disallow values not announced in vidioc_enum_fmt */
+		pix_fmt->colorspace = frm->pix.colorspace;
+		pix_fmt->xfer_func = frm->pix.xfer_func;
+	}
+
+	hw->adjust_and_map_format(ctx, pix_fmt, V4L2_TYPE_IS_OUTPUT(f->type));
+
+	v4l2_apply_frmsize_constraints(&pix_fmt->width, &pix_fmt->height, &frmsize);
+	v4l2_fill_pixfmt_mp_aligned(pix_fmt, pix_fmt->pixelformat,
+				    pix_fmt->width, pix_fmt->height, hw->stride_alignment);
+	pix_fmt->field = V4L2_FIELD_NONE;
+
+	return 0;
+}
+
+static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix_fmt = &f->fmt.pix_mp;
+	struct rga_ctx *ctx = file_to_rga_ctx(file);
+	struct rockchip_rga *rga = ctx->rga;
+	struct vb2_queue *vq;
+	struct rga_frame *frm;
+	int ret = 0;
+	int i;
+
+	/* Adjust all values accordingly to the hardware capabilities
+	 * and chosen format.
+	 */
+	ret = vidioc_try_fmt(file, priv, f);
+	if (ret)
+		return ret;
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (vb2_is_busy(vq)) {
+		v4l2_err(&rga->v4l2_dev, "queue (%d) bust\n", f->type);
+		return -EBUSY;
+	}
+	frm = rga_get_frame(ctx, f->type);
+	if (IS_ERR(frm))
+		return PTR_ERR(frm);
+	frm->fmt = rga->hw->adjust_and_map_format(ctx, pix_fmt,
+						  V4L2_TYPE_IS_OUTPUT(f->type));
+
+	/*
+	 * Copy colorimetry from output to capture as required by the
+	 * v4l2-compliance tests
+	 */
+	if (V4L2_TYPE_IS_OUTPUT(f->type)) {
+		ctx->out.pix.colorspace = pix_fmt->colorspace;
+		ctx->out.pix.ycbcr_enc = pix_fmt->ycbcr_enc;
+		ctx->out.pix.quantization = pix_fmt->quantization;
+		ctx->out.pix.xfer_func = pix_fmt->xfer_func;
+	}
+
+	/* Reset crop settings */
+	frm->crop.left = 0;
+	frm->crop.top = 0;
+	frm->crop.width = pix_fmt->width;
+	frm->crop.height = pix_fmt->height;
+
+	frm->pix = *pix_fmt;
+	ctx->cmdbuf_dirty = true;
+
+	v4l2_dbg(debug, 1, &rga->v4l2_dev,
+		 "[%s] fmt - %p4cc %dx%d (stride %d)\n",
+		  V4L2_TYPE_IS_OUTPUT(f->type) ? "OUTPUT" : "CAPTURE",
+		  &pix_fmt->pixelformat, pix_fmt->width, pix_fmt->height,
+		  pix_fmt->plane_fmt[0].bytesperline);
+
+	for (i = 0; i < pix_fmt->num_planes; i++) {
+		v4l2_dbg(debug, 1, &rga->v4l2_dev,
+			 "plane[%d]: size %d, bytesperline %d\n",
+			 i, pix_fmt->plane_fmt[i].sizeimage,
+			 pix_fmt->plane_fmt[i].bytesperline);
+	}
+
+	return 0;
+}
+
+static int vidioc_g_selection(struct file *file, void *priv,
+			      struct v4l2_selection *s)
+{
+	struct rga_ctx *ctx = file_to_rga_ctx(file);
+	struct rga_frame *f;
+	bool use_frame = false;
+
+	f = rga_get_frame(ctx, s->type);
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+		if (!V4L2_TYPE_IS_CAPTURE(s->type))
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		if (!V4L2_TYPE_IS_OUTPUT(s->type))
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		if (!V4L2_TYPE_IS_CAPTURE(s->type))
+			return -EINVAL;
+		use_frame = true;
+		break;
+	case V4L2_SEL_TGT_CROP:
+		if (!V4L2_TYPE_IS_OUTPUT(s->type))
+			return -EINVAL;
+		use_frame = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (use_frame) {
+		s->r = f->crop;
+	} else {
+		s->r.left = 0;
+		s->r.top = 0;
+		s->r.width = f->pix.width;
+		s->r.height = f->pix.height;
+	}
+
+	return 0;
+}
+
+static int vidioc_s_selection(struct file *file, void *priv,
+			      struct v4l2_selection *s)
+{
+	struct rga_ctx *ctx = file_to_rga_ctx(file);
+	struct rockchip_rga *rga = ctx->rga;
+	struct rga_frame *f;
+
+	f = rga_get_frame(ctx, s->type);
+	if (IS_ERR(f))
+		return PTR_ERR(f);
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_COMPOSE:
+		/*
+		 * COMPOSE target is only valid for capture buffer type, return
+		 * error for output buffer type
+		 */
+		if (!V4L2_TYPE_IS_CAPTURE(s->type))
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_CROP:
+		/*
+		 * CROP target is only valid for output buffer type, return
+		 * error for capture buffer type
+		 */
+		if (!V4L2_TYPE_IS_OUTPUT(s->type))
+			return -EINVAL;
+		break;
+	/*
+	 * bound and default crop/compose targets are invalid targets to
+	 * try/set
+	 */
+	default:
+		return -EINVAL;
+	}
+
+	if (s->r.top < 0 || s->r.left < 0) {
+		v4l2_dbg(debug, 1, &rga->v4l2_dev,
+			 "doesn't support negative values for top & left.\n");
+		return -EINVAL;
+	}
+
+	if (s->r.left + s->r.width > f->pix.width ||
+	    s->r.top + s->r.height > f->pix.height ||
+	    s->r.width < rga->hw->min_width || s->r.height < rga->hw->min_height) {
+		v4l2_dbg(debug, 1, &rga->v4l2_dev, "unsupported crop value.\n");
+		return -EINVAL;
+	}
+
+	if (vb2_is_streaming(v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx)) &&
+	    vb2_is_streaming(v4l2_m2m_get_src_vq(ctx->fh.m2m_ctx))) {
+		int ret = 0;
+
+		if (V4L2_TYPE_IS_OUTPUT(s->type))
+			ret = rga_check_scaling(rga->hw, &s->r, &ctx->out.crop,
+						ctx->rotate);
+		else
+			ret = rga_check_scaling(rga->hw, &ctx->in.crop, &s->r,
+						ctx->rotate);
+
+		if (ret < 0)
+			return ret;
+	}
+
+	f->crop = s->r;
+	ctx->cmdbuf_dirty = true;
+
+	return 0;
+}
+
+static const struct v4l2_ioctl_ops rga_ioctl_ops = {
+	.vidioc_querycap = vidioc_querycap,
+
+	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt,
+	.vidioc_g_fmt_vid_cap_mplane = vidioc_g_fmt,
+	.vidioc_try_fmt_vid_cap_mplane = vidioc_try_fmt,
+	.vidioc_s_fmt_vid_cap_mplane = vidioc_s_fmt,
+
+	.vidioc_enum_fmt_vid_out = vidioc_enum_fmt,
+	.vidioc_g_fmt_vid_out_mplane = vidioc_g_fmt,
+	.vidioc_try_fmt_vid_out_mplane = vidioc_try_fmt,
+	.vidioc_s_fmt_vid_out_mplane = vidioc_s_fmt,
+
+	.vidioc_reqbufs = v4l2_m2m_ioctl_reqbufs,
+	.vidioc_querybuf = v4l2_m2m_ioctl_querybuf,
+	.vidioc_qbuf = v4l2_m2m_ioctl_qbuf,
+	.vidioc_dqbuf = v4l2_m2m_ioctl_dqbuf,
+	.vidioc_prepare_buf = v4l2_m2m_ioctl_prepare_buf,
+	.vidioc_create_bufs = v4l2_m2m_ioctl_create_bufs,
+	.vidioc_expbuf = v4l2_m2m_ioctl_expbuf,
+
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+
+	.vidioc_streamon = v4l2_m2m_ioctl_streamon,
+	.vidioc_streamoff = v4l2_m2m_ioctl_streamoff,
+
+	.vidioc_g_selection = vidioc_g_selection,
+	.vidioc_s_selection = vidioc_s_selection,
+};
+
+static const struct video_device rga_videodev = {
+	.name = "rockchip-rga",
+	.fops = &rga_fops,
+	.ioctl_ops = &rga_ioctl_ops,
+	.minor = -1,
+	.release = video_device_release,
+	.vfl_dir = VFL_DIR_M2M,
+	.device_caps = V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_STREAMING,
+};
+
+static int rga_parse_dt(struct rockchip_rga *rga)
+{
+	struct reset_control *core_rst, *axi_rst, *ahb_rst;
+	int ret;
+
+	core_rst = devm_reset_control_get(rga->dev, "core");
+	if (IS_ERR(core_rst)) {
+		dev_err(rga->dev, "failed to get core reset controller\n");
+		return PTR_ERR(core_rst);
+	}
+
+	axi_rst = devm_reset_control_get(rga->dev, "axi");
+	if (IS_ERR(axi_rst)) {
+		dev_err(rga->dev, "failed to get axi reset controller\n");
+		return PTR_ERR(axi_rst);
+	}
+
+	ahb_rst = devm_reset_control_get(rga->dev, "ahb");
+	if (IS_ERR(ahb_rst)) {
+		dev_err(rga->dev, "failed to get ahb reset controller\n");
+		return PTR_ERR(ahb_rst);
+	}
+
+	reset_control_assert(core_rst);
+	udelay(1);
+	reset_control_deassert(core_rst);
+
+	reset_control_assert(axi_rst);
+	udelay(1);
+	reset_control_deassert(axi_rst);
+
+	reset_control_assert(ahb_rst);
+	udelay(1);
+	reset_control_deassert(ahb_rst);
+
+	ret = devm_clk_bulk_get_all(rga->dev, &rga->clks);
+	if (ret < 0) {
+		dev_err(rga->dev, "failed to get clocks\n");
+		return ret;
+	}
+	rga->num_clks = ret;
+
+	return 0;
+}
+
+/*
+ * Some SoCs, like RK3588 have multiple identical RGA3 cores, but the
+ * kernel is currently missing support for multi-core handling. Exposing
+ * separate devices for each core to userspace is bad, since that does
+ * not allow scheduling tasks properly (and creates ABI). With this workaround
+ * the driver will only probe for the first core and early exit for the other
+ * cores. Once the driver gains multi-core support, the same technique
+ * for detecting the main core can be used to cluster all cores together.
+ */
+static int rga_disable_multicore(struct device *dev)
+{
+	struct device_node *node = NULL;
+	const char *compatible;
+	bool is_main_core;
+	int ret;
+
+	/* Intentionally ignores the fallback strings */
+	ret = of_property_read_string(dev->of_node, "compatible", &compatible);
+	if (ret)
+		return ret;
+
+	/* The first compatible and available node found is considered the main core */
+	do {
+		node = of_find_compatible_node(node, NULL, compatible);
+		if (of_device_is_available(node))
+			break;
+	} while (node);
+
+	if (!node)
+		return -EINVAL;
+
+	is_main_core = (dev->of_node == node);
+
+	of_node_put(node);
+
+	if (!is_main_core) {
+		dev_info(dev, "missing multi-core support, ignoring this instance\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int rga_probe(struct platform_device *pdev)
+{
+	struct rockchip_rga *rga;
+	struct video_device *vfd;
+	int ret = 0;
+	int irq;
+
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	ret = rga_disable_multicore(&pdev->dev);
+	if (ret)
+		return ret;
+
+	rga = devm_kzalloc(&pdev->dev, sizeof(*rga), GFP_KERNEL);
+	if (!rga)
+		return -ENOMEM;
+
+	rga->hw = of_device_get_match_data(&pdev->dev);
+	if (!rga->hw)
+		return dev_err_probe(&pdev->dev, -ENODEV, "failed to get match data\n");
+
+	rga->dev = &pdev->dev;
+	spin_lock_init(&rga->ctrl_lock);
+	mutex_init(&rga->mutex);
+
+	ret = rga_parse_dt(rga);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Unable to parse OF data\n");
+
+	pm_runtime_enable(rga->dev);
+
+	rga->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(rga->regs)) {
+		ret = PTR_ERR(rga->regs);
+		goto err_put_clk;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = irq;
+		goto err_put_clk;
+	}
+
+	ret = devm_request_irq(rga->dev, irq, rga_isr,
+			       rga_has_internal_iommu(rga) ? 0 : IRQF_SHARED,
+			       dev_name(rga->dev), rga);
+	if (ret < 0) {
+		dev_err(rga->dev, "failed to request irq\n");
+		goto err_put_clk;
+	}
+
+	ret = dma_set_mask_and_coherent(rga->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(rga->dev, "32-bit DMA not supported");
+		goto err_put_clk;
+	}
+
+	ret = v4l2_device_register(&pdev->dev, &rga->v4l2_dev);
+	if (ret)
+		goto err_put_clk;
+	vfd = video_device_alloc();
+	if (!vfd) {
+		v4l2_err(&rga->v4l2_dev, "Failed to allocate video device\n");
+		ret = -ENOMEM;
+		goto unreg_v4l2_dev;
+	}
+	*vfd = rga_videodev;
+	vfd->lock = &rga->mutex;
+	vfd->v4l2_dev = &rga->v4l2_dev;
+
+	video_set_drvdata(vfd, rga);
+	rga->vfd = vfd;
+
+	platform_set_drvdata(pdev, rga);
+	rga->m2m_dev = v4l2_m2m_init(&rga_m2m_ops);
+	if (IS_ERR(rga->m2m_dev)) {
+		v4l2_err(&rga->v4l2_dev, "Failed to init mem2mem device\n");
+		ret = PTR_ERR(rga->m2m_dev);
+		goto rel_vdev;
+	}
+
+	ret = pm_runtime_resume_and_get(rga->dev);
+	if (ret < 0)
+		goto rel_m2m;
+
+	rga->hw->get_version(rga);
+
+	v4l2_info(&rga->v4l2_dev, "HW Version: 0x%02x.%02x\n",
+		  rga->version.major, rga->version.minor);
+
+	pm_runtime_put(rga->dev);
+
+	ret = video_register_device(vfd, VFL_TYPE_VIDEO, -1);
+	if (ret) {
+		v4l2_err(&rga->v4l2_dev, "Failed to register video device\n");
+		goto rel_m2m;
+	}
+
+	v4l2_info(&rga->v4l2_dev, "Registered %s as /dev/%s\n",
+		  vfd->name, video_device_node_name(vfd));
+
+	return 0;
+
+rel_m2m:
+	v4l2_m2m_release(rga->m2m_dev);
+rel_vdev:
+	video_device_release(vfd);
+unreg_v4l2_dev:
+	v4l2_device_unregister(&rga->v4l2_dev);
+err_put_clk:
+	pm_runtime_disable(rga->dev);
+
+	return ret;
+}
+
+static void rga_remove(struct platform_device *pdev)
+{
+	struct rockchip_rga *rga = platform_get_drvdata(pdev);
+
+	v4l2_info(&rga->v4l2_dev, "Removing\n");
+
+	v4l2_m2m_release(rga->m2m_dev);
+	video_unregister_device(rga->vfd);
+	v4l2_device_unregister(&rga->v4l2_dev);
+
+	pm_runtime_disable(rga->dev);
+}
+
+static int __maybe_unused rga_runtime_suspend(struct device *dev)
+{
+	struct rockchip_rga *rga = dev_get_drvdata(dev);
+
+	clk_bulk_disable_unprepare(rga->num_clks, rga->clks);
+
+	return 0;
+}
+
+static int __maybe_unused rga_runtime_resume(struct device *dev)
+{
+	struct rockchip_rga *rga = dev_get_drvdata(dev);
+
+	return clk_bulk_prepare_enable(rga->num_clks, rga->clks);
+}
+
+static const struct dev_pm_ops rga_pm = {
+	SET_RUNTIME_PM_OPS(rga_runtime_suspend,
+			   rga_runtime_resume, NULL)
+};
+
+static const struct of_device_id rockchip_rga_match[] = {
+	{
+		.compatible = "rockchip,rk3288-rga",
+		.data = &rga2_hw,
+	},
+	{
+		.compatible = "rockchip,rk3399-rga",
+		.data = &rga2_hw,
+	},
+	{
+		.compatible = "rockchip,rk3588-rga3",
+		.data = &rga3_hw,
+	},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, rockchip_rga_match);
+
+static struct platform_driver rga_pdrv = {
+	.probe = rga_probe,
+	.remove = rga_remove,
+	.driver = {
+		.name = RGA_NAME,
+		.pm = &rga_pm,
+		.of_match_table = rockchip_rga_match,
+	},
+};
+
+module_platform_driver(rga_pdrv);
+
+MODULE_AUTHOR("Jacob Chen <jacob-chen@iotwrt.com>");
+MODULE_DESCRIPTION("Rockchip Raster 2d Graphic Acceleration Unit");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/media/platform/rockchip/rga/rga.h

@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) Rockchip Electronics Co., Ltd.
+ * Author: Jacob Chen <jacob-chen@iotwrt.com>
+ */
+#ifndef __RGA_H__
+#define __RGA_H__
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <media/videobuf2-v4l2.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+#define RGA_NAME "rockchip-rga"
+
+#define DEFAULT_WIDTH 100
+#define DEFAULT_HEIGHT 100
+
+struct rga_frame {
+	/* Crop */
+	struct v4l2_rect crop;
+
+	/* Image format */
+	void *fmt;
+	struct v4l2_pix_format_mplane pix;
+};
+
+struct rga_dma_desc {
+	u32 addr;
+};
+
+struct rockchip_rga_version {
+	u32 major;
+	u32 minor;
+};
+
+struct rga_ctx {
+	struct v4l2_fh fh;
+	struct rockchip_rga *rga;
+	struct rga_frame in;
+	struct rga_frame out;
+	struct v4l2_ctrl_handler ctrl_handler;
+
+	void *cmdbuf_virt;
+	dma_addr_t cmdbuf_phy;
+	bool cmdbuf_dirty;
+
+	int osequence;
+	int csequence;
+
+	/* Control values */
+	u32 op;
+	u32 hflip;
+	u32 vflip;
+	u32 rotate;
+	u32 fill_color;
+};
+
+static inline struct rga_ctx *file_to_rga_ctx(struct file *filp)
+{
+	return container_of(file_to_v4l2_fh(filp), struct rga_ctx, fh);
+}
+
+struct rga_hw;
+
+struct rockchip_rga {
+	struct v4l2_device v4l2_dev;
+	struct v4l2_m2m_dev *m2m_dev;
+	struct video_device *vfd;
+
+	struct device *dev;
+	struct regmap *grf;
+	void __iomem *regs;
+	struct clk_bulk_data *clks;
+	int num_clks;
+	struct rockchip_rga_version version;
+
+	/* vfd lock */
+	struct mutex mutex;
+	/* ctrl parm lock */
+	spinlock_t ctrl_lock;
+
+	struct rga_ctx *curr;
+
+	const struct rga_hw *hw;
+};
+
+struct rga_addrs {
+	dma_addr_t y_addr;
+	dma_addr_t u_addr;
+	dma_addr_t v_addr;
+};
+
+struct rga_vb_buffer {
+	struct vb2_v4l2_buffer vb_buf;
+	struct list_head queue;
+
+	/* RGA MMU mapping for this buffer */
+	struct rga_dma_desc *dma_desc;
+	dma_addr_t dma_desc_pa;
+	size_t n_desc;
+
+	/* Plane DMA addresses after the MMU mapping of the buffer */
+	struct rga_addrs dma_addrs;
+};
+
+static inline struct rga_vb_buffer *vb_to_rga(struct vb2_v4l2_buffer *vb)
+{
+	return container_of(vb, struct rga_vb_buffer, vb_buf);
+}
+
+struct rga_frame *rga_get_frame(struct rga_ctx *ctx, enum v4l2_buf_type type);
+
+int rga_check_scaling(const struct rga_hw *hw, const struct v4l2_rect *crop_in,
+		      const struct v4l2_rect *crop_out, u32 rotate);
+
+/* RGA Buffers Manage */
+extern const struct vb2_ops rga_qops;
+
+/* RGA Hardware */
+static inline void rga_write(struct rockchip_rga *rga, u32 reg, u32 value)
+{
+	writel(value, rga->regs + reg);
+};
+
+static inline u32 rga_read(struct rockchip_rga *rga, u32 reg)
+{
+	return readl(rga->regs + reg);
+};
+
+static inline void rga_mod(struct rockchip_rga *rga, u32 reg, u32 val, u32 mask)
+{
+	u32 temp = rga_read(rga, reg) & ~(mask);
+
+	temp |= val & mask;
+	rga_write(rga, reg, temp);
+};
+
+#define RGA_FEATURE_FLIP	BIT(0)
+#define RGA_FEATURE_ROTATE	BIT(1)
+#define RGA_FEATURE_BG_COLOR	BIT(2)
+
+struct rga_hw {
+	const char *card_type;
+	bool has_internal_iommu;
+	size_t cmdbuf_size;
+	u32 min_width, min_height;
+	u32 max_width, max_height;
+	u8 max_scaling_factor;
+	u8 stride_alignment;
+	u8 features;
+
+	void (*setup_cmdbuf)(struct rga_ctx *ctx);
+	void (*start)(struct rockchip_rga *rga,
+		      struct rga_vb_buffer *src, struct rga_vb_buffer *dst);
+	bool (*handle_irq)(struct rockchip_rga *rga);
+	void (*get_version)(struct rockchip_rga *rga);
+	void *(*adjust_and_map_format)(struct rga_ctx *ctx,
+				       struct v4l2_pix_format_mplane *format,
+				       bool is_output);
+	int (*enum_format)(struct v4l2_fmtdesc *f);
+};
+
+static inline bool rga_has_internal_iommu(const struct rockchip_rga *rga)
+{
+	return rga->hw->has_internal_iommu;
+}
+
+extern const struct rga_hw rga2_hw;
+extern const struct rga_hw rga3_hw;
+
+#endif

linux-7.2.3/drivers/media/platform/rockchip/rga/rga3-hw.c

@@ -0,0 +1,507 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025-2026 Pengutronix e.K.
+ * Author: Sven Püschel <s.pueschel@pengutronix.de>
+ */
+
+#include <linux/pm_runtime.h>
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/printk.h>
+
+#include <media/v4l2-common.h>
+
+#include "rga3-hw.h"
+#include "rga.h"
+
+static unsigned int rga3_get_scaling(unsigned int src, unsigned int dst)
+{
+	/*
+	 * RGA3 scaling factor calculation as described in chapter 5.4.7 Resize
+	 * of the TRM Part 2. The resulting scaling factor is a 16-bit value
+	 * and therefore normalized with 2^16.
+	 *
+	 * While the TRM also mentions (dst-1)/(src-1) for the up-scaling case,
+	 * it didn't work as the value always exceeds 16 bit. Flipping the
+	 * factors results in a correct up-scaling. This is possible as the
+	 * RGA3 has the RGA3_WIN_SCALE_XXX_UP bit to determine if it does
+	 * an up or downscale.
+	 *
+	 * The scaling factor can potentially cause a slightly larger scaling
+	 * (e.g. 1/2px larger scale and then cropped to the destination size).
+	 * This can be seen when scaling 128x128px RGBA to 256x256px RGBA.
+	 * The RGA2 scaling factor calculation (without the various +/-1
+	 * doesn't work for the RGA3. It's assumed that this is an hardware
+	 * accuracy limitation, as the vendor kernel driver uses the same
+	 * scaling factor calculation.
+	 *
+	 * With a scaling factor of 1.0 the calculation technically also
+	 * overflows 16 bit. This isn't relevant, as in this case the
+	 * RGA3_WIN_SCALE_XXX_BYPASS bit completely skips the scaling operation.
+	 */
+	if (dst > src) {
+		if (((src - 1) << 16) % (dst - 1) == 0)
+			return ((src - 1) << 16) / (dst - 1) - 1;
+		else
+			return ((src - 1) << 16) / (dst - 1);
+	} else {
+		return ((dst - 1) << 16) / (src - 1) + 1;
+	}
+}
+
+/*
+ * Check if the given format can be captured, as the RGA3 doesn't support all
+ * input formats also on it's output.
+ */
+static bool rga3_can_capture(const struct rga3_fmt *fmt)
+{
+	return fmt->hw_format <= RGA3_COLOR_FMT_LAST_OUTPUT;
+}
+
+/*
+ * Map the transformations to the RGA3 command buffer.
+ * Currently this is just the scaling settings and a fixed alpha value.
+ */
+static void rga3_cmd_set_trans_info(struct rga_ctx *ctx)
+{
+	u32 *cmd = ctx->cmdbuf_virt;
+	unsigned int src_h, src_w, dst_h, dst_w;
+	unsigned int reg;
+	u16 hor_scl_fac, ver_scl_fac;
+	const struct rga3_fmt *in = ctx->in.fmt;
+
+	/* Support basic input cropping to support 1088px inputs */
+	src_h = ctx->in.crop.height;
+	src_w = ctx->in.crop.width;
+	dst_h = ctx->out.pix.height;
+	dst_w = ctx->out.pix.width;
+
+	reg = RGA3_WIN0_RD_CTRL - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] |= FIELD_PREP(RGA3_WIN_SCALE_HOR_UP, dst_w > src_w)
+		      |  FIELD_PREP(RGA3_WIN_SCALE_HOR_BYPASS, dst_w == src_w)
+		      |  FIELD_PREP(RGA3_WIN_SCALE_VER_UP, dst_h > src_h)
+		      |  FIELD_PREP(RGA3_WIN_SCALE_VER_BYPASS, dst_h == src_h);
+
+	hor_scl_fac = rga3_get_scaling(src_w, dst_w);
+	ver_scl_fac = rga3_get_scaling(src_h, dst_h);
+	reg = RGA3_WIN0_SCL_FAC - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = FIELD_PREP(RGA3_SCALE_HOR_FAC, hor_scl_fac)
+		      | FIELD_PREP(RGA3_SCALE_VER_FAC, ver_scl_fac);
+
+	if (v4l2_format_info(in->fourcc)->has_alpha) {
+		/* copy alpha from input */
+		reg = RGA3_OVLP_TOP_ALPHA - RGA3_FIRST_CMD_REG;
+		cmd[reg >> 2] = FIELD_PREP(RGA3_ALPHA_SELECT_MODE, 1)
+			      | FIELD_PREP(RGA3_ALPHA_BLEND_MODE, 1);
+		reg = RGA3_OVLP_BOT_ALPHA - RGA3_FIRST_CMD_REG;
+		cmd[reg >> 2] = FIELD_PREP(RGA3_ALPHA_SELECT_MODE, 1)
+			      | FIELD_PREP(RGA3_ALPHA_BLEND_MODE, 1);
+	} else {
+		/* just use a 255 alpha value */
+		reg = RGA3_OVLP_TOP_CTRL - RGA3_FIRST_CMD_REG;
+		cmd[reg >> 2] = FIELD_PREP(RGA3_OVLP_GLOBAL_ALPHA, 0xff)
+			      | FIELD_PREP(RGA3_OVLP_COLOR_MODE, 1);
+		reg = RGA3_OVLP_BOT_CTRL - RGA3_FIRST_CMD_REG;
+		cmd[reg >> 2] = FIELD_PREP(RGA3_OVLP_GLOBAL_ALPHA, 0xff)
+			      | FIELD_PREP(RGA3_OVLP_COLOR_MODE, 1);
+	}
+}
+
+static void rga3_cmd_set_win0_addr(struct rga_ctx *ctx,
+				   const struct rga_addrs *addrs)
+{
+	u32 *cmd = ctx->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA3_WIN0_Y_BASE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = addrs->y_addr;
+	reg = RGA3_WIN0_U_BASE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = addrs->u_addr;
+}
+
+static void rga3_cmd_set_wr_addr(struct rga_ctx *ctx,
+				 const struct rga_addrs *addrs)
+{
+	u32 *cmd = ctx->cmdbuf_virt;
+	unsigned int reg;
+
+	reg = RGA3_WR_Y_BASE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = addrs->y_addr;
+	reg = RGA3_WR_U_BASE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = addrs->u_addr;
+}
+
+/* Map the input pixel format to win0 of the comamnd buffer. */
+static void rga3_cmd_set_win0_format(struct rga_ctx *ctx)
+{
+	u32 *cmd = ctx->cmdbuf_virt;
+	const struct rga3_fmt *in = ctx->in.fmt;
+	const struct rga3_fmt *out = ctx->out.fmt;
+	const struct v4l2_format_info *in_fmt, *out_fmt;
+	unsigned int act_h, act_w, src_h, src_w;
+	bool r2y, y2r;
+	u8 rd_format;
+	const struct v4l2_pix_format_mplane *csc_pix;
+	u8 csc_mode;
+	unsigned int reg;
+
+	act_h = ctx->in.pix.height;
+	act_w = ctx->in.pix.width;
+	/* Support basic input cropping to support 1088px inputs */
+	src_h = ctx->in.crop.height;
+	src_w = ctx->in.crop.width;
+
+	in_fmt = v4l2_format_info(in->fourcc);
+	out_fmt = v4l2_format_info(out->fourcc);
+	r2y = v4l2_is_format_rgb(in_fmt) && v4l2_is_format_yuv(out_fmt);
+	y2r = v4l2_is_format_yuv(in_fmt) && v4l2_is_format_rgb(out_fmt);
+
+	/* The Hardware only supports formats with 1/2 planes */
+	if (in_fmt->comp_planes == 2)
+		rd_format = RGA3_RDWR_FORMAT_SEMI_PLANAR;
+	else
+		rd_format = RGA3_RDWR_FORMAT_INTERLEAVED;
+
+	/* set pixel format and CSC */
+	csc_pix = r2y ? &ctx->out.pix : &ctx->in.pix;
+	switch (csc_pix->ycbcr_enc) {
+	case V4L2_YCBCR_ENC_BT2020:
+		csc_mode = RGA3_WIN_CSC_MODE_BT2020_L;
+		break;
+	case V4L2_YCBCR_ENC_709:
+		csc_mode = RGA3_WIN_CSC_MODE_BT709_L;
+		break;
+	default: /* should be fixed to BT601 in adjust_and_map_format */
+		if (csc_pix->quantization == V4L2_QUANTIZATION_LIM_RANGE)
+			csc_mode = RGA3_WIN_CSC_MODE_BT601_L;
+		else
+			csc_mode = RGA3_WIN_CSC_MODE_BT601_F;
+		break;
+	}
+
+	reg = RGA3_WIN0_RD_CTRL - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] |= FIELD_PREP(RGA3_WIN_ENABLE, 1)
+		      |  FIELD_PREP(RGA3_WIN_PIC_FORMAT, in->hw_format)
+		      |  FIELD_PREP(RGA3_WIN_YC_SWAP, in->yc_swap)
+		      |  FIELD_PREP(RGA3_WIN_RBUV_SWAP, in->rbuv_swap)
+		      |  FIELD_PREP(RGA3_WIN_RD_FORMAT, rd_format)
+		      |  FIELD_PREP(RGA3_WIN_R2Y, r2y)
+		      |  FIELD_PREP(RGA3_WIN_Y2R, y2r)
+		      |  FIELD_PREP(RGA3_WIN_CSC_MODE, csc_mode);
+
+	/* set stride */
+	reg = RGA3_WIN0_VIR_STRIDE - RGA3_FIRST_CMD_REG;
+	/* stride needs to be in words */
+	cmd[reg >> 2] = ctx->in.pix.plane_fmt[0].bytesperline >> 2;
+	reg = RGA3_WIN0_UV_VIR_STRIDE - RGA3_FIRST_CMD_REG;
+	/* The Hardware only supports formats with 1/2 planes */
+	if (ctx->in.pix.num_planes == 2)
+		cmd[reg >> 2] = ctx->in.pix.plane_fmt[1].bytesperline >> 2;
+	else
+		cmd[reg >> 2] = ctx->in.pix.plane_fmt[0].bytesperline >> 2;
+
+	/* set size */
+	reg = RGA3_WIN0_ACT_SIZE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = FIELD_PREP(RGA3_WIDTH, act_w)
+		      | FIELD_PREP(RGA3_HEIGHT, act_h);
+	reg = RGA3_WIN0_SRC_SIZE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = FIELD_PREP(RGA3_WIDTH, src_w)
+		      | FIELD_PREP(RGA3_HEIGHT, src_h);
+}
+
+/* Map the output pixel format to the command buffer */
+static void rga3_cmd_set_wr_format(struct rga_ctx *ctx)
+{
+	u32 *cmd = ctx->cmdbuf_virt;
+	const struct rga3_fmt *out = ctx->out.fmt;
+	const struct v4l2_format_info *out_fmt;
+	unsigned int dst_h, dst_w;
+	u8 wr_format;
+	unsigned int reg;
+
+	dst_h = ctx->out.pix.height;
+	dst_w = ctx->out.pix.width;
+
+	out_fmt = v4l2_format_info(out->fourcc);
+
+	/* The Hardware only supports formats with 1/2 planes */
+	if (out_fmt->comp_planes == 2)
+		wr_format = RGA3_RDWR_FORMAT_SEMI_PLANAR;
+	else
+		wr_format = RGA3_RDWR_FORMAT_INTERLEAVED;
+
+	/* set pixel format */
+	reg = RGA3_WR_CTRL - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = FIELD_PREP(RGA3_WR_PIC_FORMAT, out->hw_format)
+		     |  FIELD_PREP(RGA3_WR_YC_SWAP, out->yc_swap)
+		     |  FIELD_PREP(RGA3_WR_RBUV_SWAP, out->rbuv_swap)
+		     |  FIELD_PREP(RGA3_WR_FORMAT, wr_format)
+	/* Use the max value to avoid limiting the write speed */
+		     |  FIELD_PREP(RGA3_WR_SW_OUTSTANDING_MAX, 63);
+
+	/* set stride */
+	reg = RGA3_WR_VIR_STRIDE - RGA3_FIRST_CMD_REG;
+	/* stride needs to be in words */
+	cmd[reg >> 2] = ctx->out.pix.plane_fmt[0].bytesperline >> 2;
+	reg = RGA3_WR_PL_VIR_STRIDE - RGA3_FIRST_CMD_REG;
+	/* The Hardware only supports formats with 1/2 planes */
+	if (ctx->out.pix.num_planes == 2)
+		cmd[reg >> 2] = ctx->out.pix.plane_fmt[1].bytesperline >> 2;
+	else
+		cmd[reg >> 2] = ctx->out.pix.plane_fmt[0].bytesperline >> 2;
+
+	/* Set size.
+	 * As two inputs are not supported, we don't use win1.
+	 * Therefore only set the size for win0.
+	 */
+	reg = RGA3_WIN0_DST_SIZE - RGA3_FIRST_CMD_REG;
+	cmd[reg >> 2] = FIELD_PREP(RGA3_WIDTH, dst_w)
+		      | FIELD_PREP(RGA3_HEIGHT, dst_h);
+}
+
+static void rga3_hw_setup_cmdbuf(struct rga_ctx *ctx)
+{
+	memset(ctx->cmdbuf_virt, 0, RGA3_CMDBUF_SIZE);
+
+	rga3_cmd_set_win0_format(ctx);
+	rga3_cmd_set_trans_info(ctx);
+	rga3_cmd_set_wr_format(ctx);
+}
+
+static void rga3_hw_start(struct rockchip_rga *rga,
+			  struct rga_vb_buffer *src, struct rga_vb_buffer *dst)
+{
+	struct rga_ctx *ctx = rga->curr;
+
+	rga3_cmd_set_win0_addr(ctx, &src->dma_addrs);
+	rga3_cmd_set_wr_addr(ctx, &dst->dma_addrs);
+
+	rga_write(rga, RGA3_CMD_ADDR, ctx->cmdbuf_phy);
+
+	/* sync CMD buf for RGA */
+	dma_sync_single_for_device(rga->dev, ctx->cmdbuf_phy,
+				   PAGE_SIZE, DMA_BIDIRECTIONAL);
+
+	/* set to master mode and start the conversion */
+	rga_write(rga, RGA3_SYS_CTRL,
+		  FIELD_PREP(RGA3_CMD_MODE, RGA3_CMD_MODE_MASTER));
+	rga_write(rga, RGA3_INT_EN, FIELD_PREP(RGA3_INT_FRM_DONE, 1));
+	rga_write(rga, RGA3_CMD_CTRL,
+		  FIELD_PREP(RGA3_CMD_LINE_START_PULSE, 1));
+}
+
+static bool rga3_handle_irq(struct rockchip_rga *rga)
+{
+	u32 intr;
+
+	intr = rga_read(rga, RGA3_INT_RAW);
+	/* clear all interrupts */
+	rga_write(rga, RGA3_INT_CLR, intr);
+
+	return FIELD_GET(RGA3_INT_FRM_DONE, intr);
+}
+
+static void rga3_get_version(struct rockchip_rga *rga)
+{
+	u32 version = rga_read(rga, RGA3_VERSION_NUM);
+
+	rga->version.major = FIELD_GET(RGA3_VERSION_NUM_MAJOR, version);
+	rga->version.minor = FIELD_GET(RGA3_VERSION_NUM_MINOR, version);
+}
+
+static struct rga3_fmt rga3_formats[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_RGB24,
+		.hw_format = RGA3_COLOR_FMT_BGR888,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_BGR24,
+		.hw_format = RGA3_COLOR_FMT_BGR888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_ABGR32,
+		.hw_format = RGA3_COLOR_FMT_BGRA8888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_RGBA32,
+		.hw_format = RGA3_COLOR_FMT_BGRA8888,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_XBGR32,
+		.hw_format = RGA3_COLOR_FMT_BGRA8888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_RGBX32,
+		.hw_format = RGA3_COLOR_FMT_BGRA8888,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_RGB565,
+		.hw_format = RGA3_COLOR_FMT_BGR565,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.hw_format = RGA3_COLOR_FMT_YUV420,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV12,
+		.hw_format = RGA3_COLOR_FMT_YUV420,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV21M,
+		.hw_format = RGA3_COLOR_FMT_YUV420,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV21,
+		.hw_format = RGA3_COLOR_FMT_YUV420,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV16M,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV16,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV61M,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV61,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YUYV,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+		.yc_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YVYU,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+		.yc_swap = 1,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_UYVY,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_VYUY,
+		.hw_format = RGA3_COLOR_FMT_YUV422,
+		.rbuv_swap = 1,
+	},
+	/* Input only formats last to keep rga3_enum_format simple */
+	{
+		.fourcc = V4L2_PIX_FMT_ARGB32,
+		.hw_format = RGA3_COLOR_FMT_ABGR8888,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_BGRA32,
+		.hw_format = RGA3_COLOR_FMT_ABGR8888,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_XRGB32,
+		.hw_format = RGA3_COLOR_FMT_ABGR8888,
+		.rbuv_swap = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_BGRX32,
+		.hw_format = RGA3_COLOR_FMT_ABGR8888,
+	},
+};
+
+static int rga3_enum_format(struct v4l2_fmtdesc *f)
+{
+	struct rga3_fmt *fmt;
+
+	if (f->index >= ARRAY_SIZE(rga3_formats))
+		return -EINVAL;
+
+	fmt = &rga3_formats[f->index];
+	if (V4L2_TYPE_IS_CAPTURE(f->type) && !rga3_can_capture(fmt))
+		return -EINVAL;
+
+	f->pixelformat = fmt->fourcc;
+	return 0;
+}
+
+static void *rga3_adjust_and_map_format(struct rga_ctx *ctx,
+					struct v4l2_pix_format_mplane *format,
+					bool is_output)
+{
+	unsigned int i;
+	const struct v4l2_format_info *format_info;
+	const struct v4l2_pix_format_mplane *other_format;
+	const struct v4l2_format_info *other_format_info;
+
+	if (!format)
+		return &rga3_formats[0];
+
+	format_info = v4l2_format_info(format->pixelformat);
+	other_format = is_output ? &ctx->out.pix : &ctx->in.pix;
+	other_format_info = v4l2_format_info(other_format->pixelformat);
+
+	if ((v4l2_is_format_rgb(format_info) &&
+	     v4l2_is_format_yuv(other_format_info)) ||
+	    (v4l2_is_format_yuv(format_info) &&
+	     v4l2_is_format_rgb(other_format_info))) {
+		/*
+		 * The RGA3 only supports BT601, BT709 and BT2020 RGB<->YUV conversions
+		 * Additionally BT709 and BT2020 only support limited range YUV.
+		 */
+		switch (format->ycbcr_enc) {
+		case V4L2_YCBCR_ENC_601:
+			/* supports full and limited range */
+			break;
+		case V4L2_YCBCR_ENC_709:
+		case V4L2_YCBCR_ENC_BT2020:
+			format->quantization = V4L2_QUANTIZATION_LIM_RANGE;
+			break;
+		default:
+			format->ycbcr_enc = V4L2_YCBCR_ENC_601;
+			format->quantization = V4L2_QUANTIZATION_FULL_RANGE;
+			break;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rga3_formats); i++) {
+		if (!is_output && !rga3_can_capture(&rga3_formats[i]))
+			continue;
+
+		if (rga3_formats[i].fourcc == format->pixelformat)
+			return &rga3_formats[i];
+	}
+
+	format->pixelformat = rga3_formats[0].fourcc;
+	return &rga3_formats[0];
+}
+
+const struct rga_hw rga3_hw = {
+	.card_type = "rga3",
+	.has_internal_iommu = false,
+	.cmdbuf_size = RGA3_CMDBUF_SIZE,
+	.min_width = RGA3_MIN_WIDTH,
+	.min_height = RGA3_MIN_HEIGHT,
+	/* use output size, as it's a bit smaller than the input size */
+	.max_width = RGA3_MAX_OUTPUT_WIDTH,
+	.max_height = RGA3_MAX_OUTPUT_HEIGHT,
+	.max_scaling_factor = RGA3_MAX_SCALING_FACTOR,
+	.stride_alignment = 16,
+	.features = 0,
+
+	.setup_cmdbuf = rga3_hw_setup_cmdbuf,
+	.start = rga3_hw_start,
+	.handle_irq = rga3_handle_irq,
+	.get_version = rga3_get_version,
+	.enum_format = rga3_enum_format,
+	.adjust_and_map_format = rga3_adjust_and_map_format,
+};

linux-7.2.3/drivers/media/platform/rockchip/rga/rga3-hw.h

@@ -0,0 +1,192 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) Pengutronix e.K.
+ * Author: Sven Püschel <s.pueschel@pengutronix.de>
+ */
+#ifndef __RGA3_HW_H__
+#define __RGA3_HW_H__
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define RGA3_CMDBUF_SIZE 0xb8
+
+#define RGA3_MIN_WIDTH 128
+#define RGA3_MIN_HEIGHT 128
+#define RGA3_MAX_INPUT_WIDTH (8192 - 16)
+#define RGA3_MAX_INPUT_HEIGHT (8192 - 16)
+#define RGA3_MAX_OUTPUT_WIDTH (8192 - 64)
+#define RGA3_MAX_OUTPUT_HEIGHT (8192 - 64)
+#define RGA3_MAX_SCALING_FACTOR 8
+#define RGA3_RESET_TIMEOUT 1000
+
+/* Registers address */
+/* sys reg */
+#define RGA3_SYS_CTRL				0x000
+#define RGA3_CMD_CTRL				0x004
+#define RGA3_CMD_ADDR				0x008
+#define RGA3_MI_GROUP_CTRL			0x00c
+#define RGA3_ARQOS_CTRL				0x010
+#define RGA3_VERSION_NUM			0x018
+#define RGA3_VERSION_TIM			0x01c
+#define RGA3_INT_EN				0x020
+#define RGA3_INT_RAW				0x024
+#define RGA3_INT_MSK				0x028
+#define RGA3_INT_CLR				0x02c
+#define RGA3_RO_SRST				0x030
+#define RGA3_STATUS0				0x034
+#define RGA3_SCAN_CNT				0x038
+#define RGA3_CMD_STATE				0x040
+
+/* cmd reg */
+#define RGA3_WIN0_RD_CTRL			0x100
+#define RGA3_FIRST_CMD_REG			RGA3_WIN0_RD_CTRL
+#define RGA3_WIN0_Y_BASE			0x110
+#define RGA3_WIN0_U_BASE			0x114
+#define RGA3_WIN0_V_BASE			0x118
+#define RGA3_WIN0_VIR_STRIDE			0x11c
+#define RGA3_WIN0_FBC_OFF			0x120
+#define RGA3_WIN0_SRC_SIZE			0x124
+#define RGA3_WIN0_ACT_OFF			0x128
+#define RGA3_WIN0_ACT_SIZE			0x12c
+#define RGA3_WIN0_DST_SIZE			0x130
+#define RGA3_WIN0_SCL_FAC			0x134
+#define RGA3_WIN0_UV_VIR_STRIDE			0x138
+#define RGA3_WIN1_RD_CTRL			0x140
+#define RGA3_WIN1_Y_BASE			0x150
+#define RGA3_WIN1_U_BASE			0x154
+#define RGA3_WIN1_V_BASE			0x158
+#define RGA3_WIN1_VIR_STRIDE			0x15c
+#define RGA3_WIN1_FBC_OFF			0x160
+#define RGA3_WIN1_SRC_SIZE			0x164
+#define RGA3_WIN1_ACT_OFF			0x168
+#define RGA3_WIN1_ACT_SIZE			0x16c
+#define RGA3_WIN1_DST_SIZE			0x170
+#define RGA3_WIN1_SCL_FAC			0x174
+#define RGA3_WIN1_UV_VIR_STRIDE			0x178
+#define RGA3_OVLP_CTRL				0x180
+#define RGA3_OVLP_OFF				0x184
+#define RGA3_OVLP_TOP_KEY_MIN			0x188
+#define RGA3_OVLP_TOP_KEY_MAX			0x18c
+#define RGA3_OVLP_TOP_CTRL			0x190
+#define RGA3_OVLP_BOT_CTRL			0x194
+#define RGA3_OVLP_TOP_ALPHA			0x198
+#define RGA3_OVLP_BOT_ALPHA			0x19c
+#define RGA3_WR_CTRL				0x1a0
+#define RGA3_WR_FBCE_CTRL			0x1a4
+#define RGA3_WR_VIR_STRIDE			0x1a8
+#define RGA3_WR_PL_VIR_STRIDE			0x1ac
+#define RGA3_WR_Y_BASE				0x1b0
+#define RGA3_WR_U_BASE				0x1b4
+#define RGA3_WR_V_BASE				0x1b8
+
+/* Registers value */
+#define RGA3_COLOR_FMT_YUV420		0x0
+#define RGA3_COLOR_FMT_YUV422		0x1
+#define RGA3_COLOR_FMT_YUV420_10B	0x2
+#define RGA3_COLOR_FMT_YUV422_10B	0x3
+/*
+ * Use memory ordering names
+ * instead of the datasheet naming RGB formats in big endian order
+ */
+#define RGA3_COLOR_FMT_BGR565		0x4
+#define RGA3_COLOR_FMT_BGR888		0x5
+#define RGA3_COLOR_FMT_FIRST_HAS_ALPHA	RGA3_COLOR_FMT_BGRA8888
+#define RGA3_COLOR_FMT_BGRA8888		0x6
+#define RGA3_COLOR_FMT_LAST_OUTPUT	RGA3_COLOR_FMT_BGRA8888
+/* the following are only supported as inputs */
+#define RGA3_COLOR_FMT_ABGR8888		0x7
+/*
+ * the following seem to be unnecessary,
+ * as they can be achieved with RB swaps
+ */
+#define RGA3_COLOR_FMT_RGBA8888		0x8
+#define RGA3_COLOR_FMT_ARGB8888		0x9
+
+#define RGA3_RDWR_FORMAT_SEMI_PLANAR	0x1
+#define RGA3_RDWR_FORMAT_INTERLEAVED	0x2
+
+#define RGA3_CMD_MODE_MASTER 0x1
+
+#define RGA3_WIN_CSC_MODE_BT601_L 0x0
+#define RGA3_WIN_CSC_MODE_BT709_L 0x1
+#define RGA3_WIN_CSC_MODE_BT601_F 0x2
+#define RGA3_WIN_CSC_MODE_BT2020_L 0x3
+
+/* RGA masks */
+/* SYS_CTRL */
+#define RGA3_CCLK_SRESET BIT(4)
+#define RGA3_ACLK_SRESET BIT(3)
+#define RGA3_CMD_MODE BIT(1)
+
+/* CMD_CTRL */
+#define RGA3_CMD_LINE_START_PULSE BIT(0)
+
+/* VERSION_NUM */
+#define RGA3_VERSION_NUM_MAJOR GENMASK(31, 28)
+#define RGA3_VERSION_NUM_MINOR GENMASK(27, 20)
+
+/* INT_* */
+#define RGA3_INT_FRM_DONE BIT(0)
+#define RGA3_INT_DMA_READ_BUS_ERR BIT(2)
+#define RGA3_INT_WIN0_FBC_DEC_ERR BIT(5)
+#define RGA3_INT_WIN0_HOR_ERR BIT(6)
+#define RGA3_INT_WIN0_VER_ERR BIT(7)
+#define RGA3_INT_WR_VER_ERR BIT(13)
+#define RGA3_INT_WR_HOR_ERR BIT(14)
+#define RGA3_INT_WR_BUS_ERR BIT(15)
+#define RGA3_INT_WIN0_IN_FIFO_WR_ERR BIT(16)
+#define RGA3_INT_WIN0_IN_FIFO_RD_ERR BIT(17)
+#define RGA3_INT_WIN0_HOR_FIFO_WR_ERR BIT(18)
+#define RGA3_INT_WIN0_HOR_FIFO_RD_ERR BIT(19)
+#define RGA3_INT_WIN0_VER_FIFO_WR_ERR BIT(20)
+#define RGA3_INT_WIN0_VER_FIFO_RD_ERR BIT(21)
+
+/* RO_SRST */
+#define RGA3_RO_SRST_DONE GENMASK(5, 0)
+
+/* *_SIZE */
+#define RGA3_HEIGHT GENMASK(28, 16)
+#define RGA3_WIDTH GENMASK(12, 0)
+
+/* SCL_FAC */
+#define RGA3_SCALE_VER_FAC GENMASK(31, 16)
+#define RGA3_SCALE_HOR_FAC GENMASK(15, 0)
+
+/* WINx_CTRL */
+#define RGA3_WIN_CSC_MODE GENMASK(27, 26)
+#define RGA3_WIN_R2Y BIT(25)
+#define RGA3_WIN_Y2R BIT(24)
+#define RGA3_WIN_SCALE_VER_UP BIT(23)
+#define RGA3_WIN_SCALE_VER_BYPASS BIT(22)
+#define RGA3_WIN_SCALE_HOR_UP BIT(21)
+#define RGA3_WIN_SCALE_HOR_BYPASS BIT(20)
+#define RGA3_WIN_YC_SWAP BIT(13)
+#define RGA3_WIN_RBUV_SWAP BIT(12)
+#define RGA3_WIN_RD_FORMAT GENMASK(9, 8)
+#define RGA3_WIN_PIC_FORMAT GENMASK(7, 4)
+#define RGA3_WIN_ENABLE BIT(0)
+
+/* COLOR_CTRL */
+#define RGA3_OVLP_GLOBAL_ALPHA GENMASK(23, 16)
+#define RGA3_OVLP_COLOR_MODE BIT(0)
+
+/* ALPHA_CTRL */
+#define RGA3_ALPHA_SELECT_MODE BIT(4)
+#define RGA3_ALPHA_BLEND_MODE GENMASK(3, 2)
+
+/* WR_CTRL */
+#define RGA3_WR_YC_SWAP BIT(20)
+#define RGA3_WR_SW_OUTSTANDING_MAX GENMASK(18, 13)
+#define RGA3_WR_RBUV_SWAP BIT(12)
+#define RGA3_WR_FORMAT GENMASK(9, 8)
+#define RGA3_WR_PIC_FORMAT GENMASK(7, 4)
+
+struct rga3_fmt {
+	u32 fourcc;
+	u8 hw_format;
+	bool rbuv_swap;
+	bool yc_swap;
+};
+
+#endif