[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>

drivers/media/platform/Kconfig

@@ -458,6 +458,21 @@ config VIDEO_RENESAS_VSP1
 	  To compile this driver as a module, choose M here: the module
 	  will be called vsp1.
 
+config VIDEO_ROCKCHIP_RGA
+	tristate "Rockchip Raster 2d Graphic Acceleration Unit"
+	depends on VIDEO_DEV && VIDEO_V4L2 && HAS_DMA
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	select VIDEOBUF2_DMA_SG
+	select V4L2_MEM2MEM_DEV
+	default n
+	---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.
+
 config VIDEO_TI_VPE
 	tristate "TI VPE (Video Processing Engine) driver"
 	depends on VIDEO_DEV && VIDEO_V4L2

drivers/media/platform/Makefile

@@ -64,6 +64,8 @@ obj-$(CONFIG_VIDEO_RENESAS_FDP1)	+= rcar_fdp1.o
 obj-$(CONFIG_VIDEO_RENESAS_JPU) 	+= rcar_jpu.o
 obj-$(CONFIG_VIDEO_RENESAS_VSP1)	+= vsp1/
 
+obj-$(CONFIG_VIDEO_ROCKCHIP_RGA)	+= rockchip/rga/
+
 obj-y	+= omap/
 
 obj-$(CONFIG_VIDEO_AM437X_VPFE)		+= am437x/

drivers/media/platform/rockchip/rga/Makefile

+rockchip-rga-objs := rga.o rga-hw.o rga-buf.o
+
+obj-$(CONFIG_VIDEO_ROCKCHIP_RGA) += rockchip-rga.o

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

+/*
+ * 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);
+}

drivers/media/platform/rockchip/rga/rga.h

+/*
+ * 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_H__
+#define __RGA_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"
+
+struct rga_fmt {
+	u32 fourcc;
+	int depth;
+	u8 uv_factor;
+	u8 y_div;
+	u8 x_div;
+	u8 color_swap;
+	u8 hw_format;
+};
+
+struct rga_frame {
+	/* Original dimensions */
+	u32 width;
+	u32 height;
+	u32 colorspace;
+
+	/* Crop */
+	struct v4l2_rect crop;
+
+	/* Image format */
+	struct rga_fmt *fmt;
+
+	/* Variables that can calculated once and reused */
+	u32 stride;
+	u32 size;
+};
+
+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;
+
+	/* Control values */
+	u32 op;
+	u32 hflip;
+	u32 vflip;
+	u32 rotate;
+	u32 fill_color;
+};
+
+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 *sclk;
+	struct clk *aclk;
+	struct clk *hclk;
+	struct rockchip_rga_version version;
+
+	/* vfd lock */
+	struct mutex mutex;
+	/* ctrl parm lock */
+	spinlock_t ctrl_lock;
+
+	wait_queue_head_t irq_queue;
+
+	struct rga_ctx *curr;
+	dma_addr_t cmdbuf_phy;
+	void *cmdbuf_virt;
+	unsigned int *src_mmu_pages;
+	unsigned int *dst_mmu_pages;
+};
+
+struct rga_frame *rga_get_frame(struct rga_ctx *ctx, enum v4l2_buf_type type);
+
+/* RGA Buffers Manage */
+extern const struct vb2_ops rga_qops;
+void rga_buf_map(struct vb2_buffer *vb);
+
+/* 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);
+};
+
+void rga_hw_start(struct rockchip_rga *rga);
+
+#endif