[media] v4l: ti-vpe: Add VPE mem to mem driver

VPE is a block which consists of a single memory to memory path which
can perform chrominance up/down sampling, de-interlacing, scaling, and
color space conversion of raster or tiled YUV420 coplanar, YUV422
coplanar or YUV422 interleaved video formats.

We create a mem2mem driver based primarily on the mem2mem-testdev
example. The de-interlacer, scaler and color space converter are all
bypassed for now to keep the driver simple. Chroma up/down sampler
blocks are implemented, so conversion beteen different YUV formats is
possible.

Each mem2mem context allocates a buffer for VPE MMR values which it will
use when it gets access to the VPE HW via the mem2mem queue, it also
allocates a VPDMA descriptor list to which configuration and data
descriptors are added.

Based on the information received via v4l2 ioctls for the source and
destination queues, the driver configures the values for the MMRs, and
stores them in the buffer. There are also some VPDMA parameters like
frame start and line mode which needs to be configured, these are
configured by direct register writes via the VPDMA helper functions.

The driver's device_run() mem2mem op will add each descriptor based on
how the source and destination queues are set up for the given ctx, once
the list is prepared, it's submitted to VPDMA, these descriptors when
parsed by VPDMA will upload MMR registers, start DMA of video buffers on
the various input and output clients/ports.

When the list is parsed completely(and the DMAs on all the output ports
done), an interrupt is generated which we use to notify that the source
and destination buffers are done. The rest of the driver is quite
similar to other mem2mem drivers, we use the multiplane v4l2 ioctls as
the HW support coplanar formats.

Signed-off-by: Archit Taneja <archit@ti.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Kamil Debski <k.debski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>

5 files changed, 2294 insertions, 0 deletions

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 29acc2d2aee6..2405ef7c6604 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -220,6 +220,22 @@ config VIDEO_RENESAS_VSP1
 	  To compile this driver as a module, choose M here: the module
 	  will be called vsp1.
 
+config VIDEO_TI_VPE
+	tristate "TI VPE (Video Processing Engine) driver"
+	depends on VIDEO_DEV && VIDEO_V4L2 && SOC_DRA7XX
+	select VIDEOBUF2_DMA_CONTIG
+	select V4L2_MEM2MEM_DEV
+	default n
+	---help---
+	  Support for the TI VPE(Video Processing Engine) block
+	  found on DRA7XX SoC.
+
+config VIDEO_TI_VPE_DEBUG
+	bool "VPE debug messages"
+	depends on VIDEO_TI_VPE
+	---help---
+	  Enable debug messages on VPE driver.
+
 endif # V4L_MEM2MEM_DRIVERS
 
 menuconfig V4L_TEST_DRIVERS
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index 4e4da482c522..1348ba1faf92 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -22,6 +22,8 @@ obj-$(CONFIG_VIDEO_VIVI) += vivi.o
 
 obj-$(CONFIG_VIDEO_MEM2MEM_TESTDEV) += mem2mem_testdev.o
 
+obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
+
 obj-$(CONFIG_VIDEO_MX2_EMMAPRP)		+= mx2_emmaprp.o
 obj-$(CONFIG_VIDEO_CODA) 		+= coda.o
 
diff --git a/drivers/media/platform/ti-vpe/Makefile b/drivers/media/platform/ti-vpe/Makefile
new file mode 100644
index 000000000000..cbf0a806ba1d
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_VIDEO_TI_VPE) += ti-vpe.o
+
+ti-vpe-y := vpe.o vpdma.o
+
+ccflags-$(CONFIG_VIDEO_TI_VPE_DEBUG) += -DDEBUG
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
new file mode 100644
index 000000000000..3bd9ca658b54
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -0,0 +1,1775 @@
+/*
+ * TI VPE mem2mem driver, based on the virtual v4l2-mem2mem example driver
+ *
+ * Copyright (c) 2013 Texas Instruments Inc.
+ * David Griego, <dagriego@biglakesoftware.com>
+ * Dale Farnsworth, <dale@farnsworth.org>
+ * Archit Taneja, <archit@ti.com>
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ * Pawel Osciak, <pawel@osciak.com>
+ * Marek Szyprowski, <m.szyprowski@samsung.com>
+ *
+ * Based on the virtual v4l2-mem2mem example device
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioctl.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "vpdma.h"
+#include "vpe_regs.h"
+
+#define VPE_MODULE_NAME "vpe"
+
+/* minimum and maximum frame sizes */
+#define MIN_W		128
+#define MIN_H		128
+#define MAX_W		1920
+#define MAX_H		1080
+
+/* required alignments */
+#define S_ALIGN		0	/* multiple of 1 */
+#define H_ALIGN		1	/* multiple of 2 */
+#define W_ALIGN		1	/* multiple of 2 */
+
+/* multiple of 128 bits, line stride, 16 bytes */
+#define L_ALIGN		4
+
+/* flags that indicate a format can be used for capture/output */
+#define VPE_FMT_TYPE_CAPTURE	(1 << 0)
+#define VPE_FMT_TYPE_OUTPUT	(1 << 1)
+
+/* used as plane indices */
+#define VPE_MAX_PLANES	2
+#define VPE_LUMA	0
+#define VPE_CHROMA	1
+
+/* per m2m context info */
+#define VPE_DEF_BUFS_PER_JOB	1	/* default one buffer per batch job */
+
+/*
+ * each VPE context can need up to 3 config desciptors, 7 input descriptors,
+ * 3 output descriptors, and 10 control descriptors
+ */
+#define VPE_DESC_LIST_SIZE	(10 * VPDMA_DTD_DESC_SIZE +	\
+					13 * VPDMA_CFD_CTD_DESC_SIZE)
+
+#define vpe_dbg(vpedev, fmt, arg...)	\
+		dev_dbg((vpedev)->v4l2_dev.dev, fmt, ##arg)
+#define vpe_err(vpedev, fmt, arg...)	\
+		dev_err((vpedev)->v4l2_dev.dev, fmt, ##arg)
+
+struct vpe_us_coeffs {
+	unsigned short	anchor_fid0_c0;
+	unsigned short	anchor_fid0_c1;
+	unsigned short	anchor_fid0_c2;
+	unsigned short	anchor_fid0_c3;
+	unsigned short	interp_fid0_c0;
+	unsigned short	interp_fid0_c1;
+	unsigned short	interp_fid0_c2;
+	unsigned short	interp_fid0_c3;
+	unsigned short	anchor_fid1_c0;
+	unsigned short	anchor_fid1_c1;
+	unsigned short	anchor_fid1_c2;
+	unsigned short	anchor_fid1_c3;
+	unsigned short	interp_fid1_c0;
+	unsigned short	interp_fid1_c1;
+	unsigned short	interp_fid1_c2;
+	unsigned short	interp_fid1_c3;
+};
+
+/*
+ * Default upsampler coefficients
+ */
+static const struct vpe_us_coeffs us_coeffs[] = {
+	{
+		/* Coefficients for progressive input */
+		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
+		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
+	},
+};
+
+/*
+ * The port_data structure contains per-port data.
+ */
+struct vpe_port_data {
+	enum vpdma_channel channel;	/* VPDMA channel */
+	u8	vb_part;		/* plane index for co-panar formats */
+};
+
+/*
+ * Define indices into the port_data tables
+ */
+#define VPE_PORT_LUMA1_IN	0
+#define VPE_PORT_CHROMA1_IN	1
+#define VPE_PORT_LUMA_OUT	8
+#define VPE_PORT_CHROMA_OUT	9
+#define VPE_PORT_RGB_OUT	10
+
+static const struct vpe_port_data port_data[11] = {
+	[VPE_PORT_LUMA1_IN] = {
+		.channel	= VPE_CHAN_LUMA1_IN,
+		.vb_part	= VPE_LUMA,
+	},
+	[VPE_PORT_CHROMA1_IN] = {
+		.channel	= VPE_CHAN_CHROMA1_IN,
+		.vb_part	= VPE_CHROMA,
+	},
+	[VPE_PORT_LUMA_OUT] = {
+		.channel	= VPE_CHAN_LUMA_OUT,
+		.vb_part	= VPE_LUMA,
+	},
+	[VPE_PORT_CHROMA_OUT] = {
+		.channel	= VPE_CHAN_CHROMA_OUT,
+		.vb_part	= VPE_CHROMA,
+	},
+	[VPE_PORT_RGB_OUT] = {
+		.channel	= VPE_CHAN_RGB_OUT,
+		.vb_part	= VPE_LUMA,
+	},
+};
+
+
+/* driver info for each of the supported video formats */
+struct vpe_fmt {
+	char	*name;			/* human-readable name */
+	u32	fourcc;			/* standard format identifier */
+	u8	types;			/* CAPTURE and/or OUTPUT */
+	u8	coplanar;		/* set for unpacked Luma and Chroma */
+	/* vpdma format info for each plane */
+	struct vpdma_data_format const *vpdma_fmt[VPE_MAX_PLANES];
+};
+
+static struct vpe_fmt vpe_formats[] = {
+	{
+		.name		= "YUV 422 co-planar",
+		.fourcc		= V4L2_PIX_FMT_NV16,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 1,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y444],
+				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C444],
+				  },
+	},
+	{
+		.name		= "YUV 420 co-planar",
+		.fourcc		= V4L2_PIX_FMT_NV12,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 1,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420],
+				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C420],
+				  },
+	},
+	{
+		.name		= "YUYV 422 packed",
+		.fourcc		= V4L2_PIX_FMT_YUYV,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_YC422],
+				  },
+	},
+	{
+		.name		= "UYVY 422 packed",
+		.fourcc		= V4L2_PIX_FMT_UYVY,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_CY422],
+				  },
+	},
+};
+
+/*
+ * per-queue, driver-specific private data.
+ * there is one source queue and one destination queue for each m2m context.
+ */
+struct vpe_q_data {
+	unsigned int		width;				/* frame width */
+	unsigned int		height;				/* frame height */
+	unsigned int		bytesperline[VPE_MAX_PLANES];	/* bytes per line in memory */
+	enum v4l2_colorspace	colorspace;
+	unsigned int		flags;
+	unsigned int		sizeimage[VPE_MAX_PLANES];	/* image size in memory */
+	struct v4l2_rect	c_rect;				/* crop/compose rectangle */
+	struct vpe_fmt		*fmt;				/* format info */
+};
+
+/* vpe_q_data flag bits */
+#define	Q_DATA_FRAME_1D		(1 << 0)
+#define	Q_DATA_MODE_TILED	(1 << 1)
+
+enum {
+	Q_DATA_SRC = 0,
+	Q_DATA_DST = 1,
+};
+
+/* find our format description corresponding to the passed v4l2_format */
+static struct vpe_fmt *find_format(struct v4l2_format *f)
+{
+	struct vpe_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) {
+		fmt = &vpe_formats[k];
+		if (fmt->fourcc == f->fmt.pix.pixelformat)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+/*
+ * there is one vpe_dev structure in the driver, it is shared by
+ * all instances.
+ */
+struct vpe_dev {
+	struct v4l2_device	v4l2_dev;
+	struct video_device	vfd;
+	struct v4l2_m2m_dev	*m2m_dev;
+
+	atomic_t		num_instances;	/* count of driver instances */
+	dma_addr_t		loaded_mmrs;	/* shadow mmrs in device */
+	struct mutex		dev_mutex;
+	spinlock_t		lock;
+
+	int			irq;
+	void __iomem		*base;
+
+	struct vb2_alloc_ctx	*alloc_ctx;
+	struct vpdma_data	*vpdma;		/* vpdma data handle */
+};
+
+/*
+ * There is one vpe_ctx structure for each m2m context.
+ */
+struct vpe_ctx {
+	struct v4l2_fh		fh;
+	struct vpe_dev		*dev;
+	struct v4l2_m2m_ctx	*m2m_ctx;
+	struct v4l2_ctrl_handler hdl;
+
+	unsigned int		sequence;		/* current frame/field seq */
+	unsigned int		aborting;		/* abort after next irq */
+
+	unsigned int		bufs_per_job;		/* input buffers per batch */
+	unsigned int		bufs_completed;		/* bufs done in this batch */
+
+	struct vpe_q_data	q_data[2];		/* src & dst queue data */
+	struct vb2_buffer	*src_vb;
+	struct vb2_buffer	*dst_vb;
+
+	struct vpdma_buf	mmr_adb;		/* shadow reg addr/data block */
+	struct vpdma_desc_list	desc_list;		/* DMA descriptor list */
+
+	bool			load_mmrs;		/* have new shadow reg values */
+};
+
+
+/*
+ * M2M devices get 2 queues.
+ * Return the queue given the type.
+ */
+static struct vpe_q_data *get_q_data(struct vpe_ctx *ctx,
+				     enum v4l2_buf_type type)
+{
+	switch (type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		return &ctx->q_data[Q_DATA_SRC];
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		return &ctx->q_data[Q_DATA_DST];
+	default:
+		BUG();
+	}
+	return NULL;
+}
+
+static u32 read_reg(struct vpe_dev *dev, int offset)
+{
+	return ioread32(dev->base + offset);
+}
+
+static void write_reg(struct vpe_dev *dev, int offset, u32 value)
+{
+	iowrite32(value, dev->base + offset);
+}
+
+/* register field read/write helpers */
+static int get_field(u32 value, u32 mask, int shift)
+{
+	return (value & (mask << shift)) >> shift;
+}
+
+static int read_field_reg(struct vpe_dev *dev, int offset, u32 mask, int shift)
+{
+	return get_field(read_reg(dev, offset), mask, shift);
+}
+
+static void write_field(u32 *valp, u32 field, u32 mask, int shift)
+{
+	u32 val = *valp;
+
+	val &= ~(mask << shift);
+	val |= (field & mask) << shift;
+	*valp = val;
+}
+
+static void write_field_reg(struct vpe_dev *dev, int offset, u32 field,
+		u32 mask, int shift)
+{
+	u32 val = read_reg(dev, offset);
+
+	write_field(&val, field, mask, shift);
+
+	write_reg(dev, offset, val);
+}
+
+/*
+ * DMA address/data block for the shadow registers
+ */
+struct vpe_mmr_adb {
+	struct vpdma_adb_hdr	out_fmt_hdr;
+	u32			out_fmt_reg[1];
+	u32			out_fmt_pad[3];
+	struct vpdma_adb_hdr	us1_hdr;
+	u32			us1_regs[8];
+	struct vpdma_adb_hdr	us2_hdr;
+	u32			us2_regs[8];
+	struct vpdma_adb_hdr	us3_hdr;
+	u32			us3_regs[8];
+	struct vpdma_adb_hdr	dei_hdr;
+	u32			dei_regs[1];
+	u32			dei_pad[3];
+	struct vpdma_adb_hdr	sc_hdr;
+	u32			sc_regs[1];
+	u32			sc_pad[3];
+	struct vpdma_adb_hdr	csc_hdr;
+	u32			csc_regs[6];
+	u32			csc_pad[2];
+};
+
+#define VPE_SET_MMR_ADB_HDR(ctx, hdr, regs, offset_a)	\
+	VPDMA_SET_MMR_ADB_HDR(ctx->mmr_adb, vpe_mmr_adb, hdr, regs, offset_a)
+/*
+ * Set the headers for all of the address/data block structures.
+ */
+static void init_adb_hdrs(struct vpe_ctx *ctx)
+{
+	VPE_SET_MMR_ADB_HDR(ctx, out_fmt_hdr, out_fmt_reg, VPE_CLK_FORMAT_SELECT);
+	VPE_SET_MMR_ADB_HDR(ctx, us1_hdr, us1_regs, VPE_US1_R0);
+	VPE_SET_MMR_ADB_HDR(ctx, us2_hdr, us2_regs, VPE_US2_R0);
+	VPE_SET_MMR_ADB_HDR(ctx, us3_hdr, us3_regs, VPE_US3_R0);
+	VPE_SET_MMR_ADB_HDR(ctx, dei_hdr, dei_regs, VPE_DEI_FRAME_SIZE);
+	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr, sc_regs, VPE_SC_MP_SC0);
+	VPE_SET_MMR_ADB_HDR(ctx, csc_hdr, csc_regs, VPE_CSC_CSC00);
+};
+
+/*
+ * Enable or disable the VPE clocks
+ */
+static void vpe_set_clock_enable(struct vpe_dev *dev, bool on)
+{
+	u32 val = 0;
+
+	if (on)
+		val = VPE_DATA_PATH_CLK_ENABLE | VPE_VPEDMA_CLK_ENABLE;
+	write_reg(dev, VPE_CLK_ENABLE, val);
+}
+
+static void vpe_top_reset(struct vpe_dev *dev)
+{
+
+	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_DATA_PATH_CLK_RESET_MASK,
+		VPE_DATA_PATH_CLK_RESET_SHIFT);
+
+	usleep_range(100, 150);
+
+	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_DATA_PATH_CLK_RESET_MASK,
+		VPE_DATA_PATH_CLK_RESET_SHIFT);
+}
+
+static void vpe_top_vpdma_reset(struct vpe_dev *dev)
+{
+	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_VPDMA_CLK_RESET_MASK,
+		VPE_VPDMA_CLK_RESET_SHIFT);
+
+	usleep_range(100, 150);
+
+	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_VPDMA_CLK_RESET_MASK,
+		VPE_VPDMA_CLK_RESET_SHIFT);
+}
+
+/*
+ * Load the correct of upsampler coefficients into the shadow MMRs
+ */
+static void set_us_coefficients(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *us1_reg = &mmr_adb->us1_regs[0];
+	u32 *us2_reg = &mmr_adb->us2_regs[0];
+	u32 *us3_reg = &mmr_adb->us3_regs[0];
+	const unsigned short *cp, *end_cp;
+
+	cp = &us_coeffs[0].anchor_fid0_c0;
+
+	end_cp = cp + sizeof(us_coeffs[0]) / sizeof(*cp);
+
+	while (cp < end_cp) {
+		write_field(us1_reg, *cp++, VPE_US_C0_MASK, VPE_US_C0_SHIFT);
+		write_field(us1_reg, *cp++, VPE_US_C1_MASK, VPE_US_C1_SHIFT);
+		*us2_reg++ = *us1_reg;
+		*us3_reg++ = *us1_reg++;
+	}
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the upsampler config mode and the VPDMA line mode in the shadow MMRs.
+ */
+static void set_cfg_and_line_modes(struct vpe_ctx *ctx)
+{
+	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *us1_reg0 = &mmr_adb->us1_regs[0];
+	u32 *us2_reg0 = &mmr_adb->us2_regs[0];
+	u32 *us3_reg0 = &mmr_adb->us3_regs[0];
+	int line_mode = 1;
+	int cfg_mode = 1;
+
+	/*
+	 * Cfg Mode 0: YUV420 source, enable upsampler, DEI is de-interlacing.
+	 * Cfg Mode 1: YUV422 source, disable upsampler, DEI is de-interlacing.
+	 */
+
+	if (fmt->fourcc == V4L2_PIX_FMT_NV12) {
+		cfg_mode = 0;
+		line_mode = 0;		/* double lines to line buffer */
+	}
+
+	write_field(us1_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
+	write_field(us2_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
+	write_field(us3_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
+
+	/* regs for now */
+	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA1_IN);
+
+	/* frame start for input luma */
+	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
+		VPE_CHAN_LUMA1_IN);
+
+	/* frame start for input chroma */
+	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
+		VPE_CHAN_CHROMA1_IN);
+
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the shadow registers that are modified when the source
+ * format changes.
+ */
+static void set_src_registers(struct vpe_ctx *ctx)
+{
+	set_us_coefficients(ctx);
+}
+
+/*
+ * Set the shadow registers that are modified when the destination
+ * format changes.
+ */
+static void set_dst_registers(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_DST].fmt;
+	u32 val = 0;
+
+	/* select RGB path when color space conversion is supported in future */
+	if (fmt->fourcc == V4L2_PIX_FMT_RGB24)
+		val |= VPE_RGB_OUT_SELECT | VPE_CSC_SRC_DEI_SCALER;
+	else if (fmt->fourcc == V4L2_PIX_FMT_NV16)
+		val |= VPE_COLOR_SEPARATE_422;
+
+	/* The source of CHR_DS is always the scaler, whether it's used or not */
+	val |= VPE_DS_SRC_DEI_SCALER;
+
+	if (fmt->fourcc != V4L2_PIX_FMT_NV12)
+		val |= VPE_DS_BYPASS;
+
+	mmr_adb->out_fmt_reg[0] = val;
+
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the de-interlacer shadow register values
+ */
+static void set_dei_regs_bypass(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
+	unsigned int src_h = s_q_data->c_rect.height;
+	unsigned int src_w = s_q_data->c_rect.width;
+	u32 *dei_mmr0 = &mmr_adb->dei_regs[0];
+	u32 val = 0;
+
+	/*
+	 * according to TRM, we should set DEI in progressive bypass mode when
+	 * the input content is progressive, however, DEI is bypassed correctly
+	 * for both progressive and interlace content in interlace bypass mode.
+	 * It has been recommended not to use progressive bypass mode.
+	 */
+	val = VPE_DEI_INTERLACE_BYPASS;
+
+	val |= (src_h << VPE_DEI_HEIGHT_SHIFT) |
+		(src_w << VPE_DEI_WIDTH_SHIFT) |
+		VPE_DEI_FIELD_FLUSH;
+
+	*dei_mmr0 = val;
+
+	ctx->load_mmrs = true;
+}
+
+static void set_csc_coeff_bypass(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *shadow_csc_reg5 = &mmr_adb->csc_regs[5];
+
+	*shadow_csc_reg5 |= VPE_CSC_BYPASS;
+
+	ctx->load_mmrs = true;
+}
+
+static void set_sc_regs_bypass(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *sc_reg0 = &mmr_adb->sc_regs[0];
+	u32 val = 0;
+
+	val |= VPE_SC_BYPASS;
+	*sc_reg0 = val;
+
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the shadow registers whose values are modified when either the
+ * source or destination format is changed.
+ */
+static int set_srcdst_params(struct vpe_ctx *ctx)
+{
+	ctx->sequence = 0;
+
+	set_cfg_and_line_modes(ctx);
+	set_dei_regs_bypass(ctx);
+	set_csc_coeff_bypass(ctx);
+	set_sc_regs_bypass(ctx);
+
+	return 0;
+}
+
+/*
+ * Return the vpe_ctx structure for a given struct file
+ */
+static struct vpe_ctx *file2ctx(struct file *file)
+{
+	return container_of(file->private_data, struct vpe_ctx, fh);
+}
+
+/*
+ * mem2mem callbacks
+ */
+
+/**
+ * job_ready() - check whether an instance is ready to be scheduled to run
+ */
+static int job_ready(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	int needed = ctx->bufs_per_job;
+
+	if (v4l2_m2m_num_src_bufs_ready(ctx->m2m_ctx) < needed)
+		return 0;
+
+	return 1;
+}
+
+static void job_abort(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+
+	/* Will cancel the transaction in the next interrupt handler */
+	ctx->aborting = 1;
+}
+
+/*
+ * Lock access to the device
+ */
+static void vpe_lock(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	struct vpe_dev *dev = ctx->dev;
+	mutex_lock(&dev->dev_mutex);
+}
+
+static void vpe_unlock(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	struct vpe_dev *dev = ctx->dev;
+	mutex_unlock(&dev->dev_mutex);
+}
+
+static void vpe_dump_regs(struct vpe_dev *dev)
+{
+#define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r))
+
+	vpe_dbg(dev, "VPE Registers:\n");
+
+	DUMPREG(PID);
+	DUMPREG(SYSCONFIG);
+	DUMPREG(INT0_STATUS0_RAW);
+	DUMPREG(INT0_STATUS0);
+	DUMPREG(INT0_ENABLE0);
+	DUMPREG(INT0_STATUS1_RAW);
+	DUMPREG(INT0_STATUS1);
+	DUMPREG(INT0_ENABLE1);
+	DUMPREG(CLK_ENABLE);
+	DUMPREG(CLK_RESET);
+	DUMPREG(CLK_FORMAT_SELECT);
+	DUMPREG(CLK_RANGE_MAP);
+	DUMPREG(US1_R0);
+	DUMPREG(US1_R1);
+	DUMPREG(US1_R2);
+	DUMPREG(US1_R3);
+	DUMPREG(US1_R4);
+	DUMPREG(US1_R5);
+	DUMPREG(US1_R6);
+	DUMPREG(US1_R7);
+	DUMPREG(US2_R0);
+	DUMPREG(US2_R1);
+	DUMPREG(US2_R2);
+	DUMPREG(US2_R3);
+	DUMPREG(US2_R4);
+	DUMPREG(US2_R5);
+	DUMPREG(US2_R6);
+	DUMPREG(US2_R7);
+	DUMPREG(US3_R0);
+	DUMPREG(US3_R1);
+	DUMPREG(US3_R2);
+	DUMPREG(US3_R3);
+	DUMPREG(US3_R4);
+	DUMPREG(US3_R5);
+	DUMPREG(US3_R6);
+	DUMPREG(US3_R7);
+	DUMPREG(DEI_FRAME_SIZE);
+	DUMPREG(MDT_BYPASS);
+	DUMPREG(MDT_SF_THRESHOLD);
+	DUMPREG(EDI_CONFIG);
+	DUMPREG(DEI_EDI_LUT_R0);
+	DUMPREG(DEI_EDI_LUT_R1);
+	DUMPREG(DEI_EDI_LUT_R2);
+	DUMPREG(DEI_EDI_LUT_R3);
+	DUMPREG(DEI_FMD_WINDOW_R0);
+	DUMPREG(DEI_FMD_WINDOW_R1);
+	DUMPREG(DEI_FMD_CONTROL_R0);
+	DUMPREG(DEI_FMD_CONTROL_R1);
+	DUMPREG(DEI_FMD_STATUS_R0);
+	DUMPREG(DEI_FMD_STATUS_R1);
+	DUMPREG(DEI_FMD_STATUS_R2);
+	DUMPREG(SC_MP_SC0);
+	DUMPREG(SC_MP_SC1);
+	DUMPREG(SC_MP_SC2);
+	DUMPREG(SC_MP_SC3);
+	DUMPREG(SC_MP_SC4);
+	DUMPREG(SC_MP_SC5);
+	DUMPREG(SC_MP_SC6);
+	DUMPREG(SC_MP_SC8);
+	DUMPREG(SC_MP_SC9);
+	DUMPREG(SC_MP_SC10);
+	DUMPREG(SC_MP_SC11);
+	DUMPREG(SC_MP_SC12);
+	DUMPREG(SC_MP_SC13);
+	DUMPREG(SC_MP_SC17);
+	DUMPREG(SC_MP_SC18);
+	DUMPREG(SC_MP_SC19);
+	DUMPREG(SC_MP_SC20);
+	DUMPREG(SC_MP_SC21);
+	DUMPREG(SC_MP_SC22);
+	DUMPREG(SC_MP_SC23);
+	DUMPREG(SC_MP_SC24);
+	DUMPREG(SC_MP_SC25);
+	DUMPREG(CSC_CSC00);
+	DUMPREG(CSC_CSC01);
+	DUMPREG(CSC_CSC02);
+	DUMPREG(CSC_CSC03);
+	DUMPREG(CSC_CSC04);
+	DUMPREG(CSC_CSC05);
+#undef DUMPREG
+}
+
+static void add_out_dtd(struct vpe_ctx *ctx, int port)
+{
+	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_DST];
+	const struct vpe_port_data *p_data = &port_data[port];
+	struct vb2_buffer *vb = ctx->dst_vb;
+	struct v4l2_rect *c_rect = &q_data->c_rect;
+	struct vpe_fmt *fmt = q_data->fmt;
+	const struct vpdma_data_format *vpdma_fmt;
+	int plane = fmt->coplanar ? p_data->vb_part : 0;
+	dma_addr_t dma_addr;
+	u32 flags = 0;
+
+	vpdma_fmt = fmt->vpdma_fmt[plane];
+	dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
+	if (!dma_addr) {
+		vpe_err(ctx->dev,
+			"acquiring output buffer(%d) dma_addr failed\n",
+			port);
+		return;
+	}
+
+	if (q_data->flags & Q_DATA_FRAME_1D)
+		flags |= VPDMA_DATA_FRAME_1D;
+	if (q_data->flags & Q_DATA_MODE_TILED)
+		flags |= VPDMA_DATA_MODE_TILED;
+
+	vpdma_add_out_dtd(&ctx->desc_list, c_rect, vpdma_fmt, dma_addr,
+		p_data->channel, flags);
+}
+
+static void add_in_dtd(struct vpe_ctx *ctx, int port)
+{
+	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_SRC];
+	const struct vpe_port_data *p_data = &port_data[port];
+	struct vb2_buffer *vb = ctx->src_vb;
+	struct v4l2_rect *c_rect = &q_data->c_rect;
+	struct vpe_fmt *fmt = q_data->fmt;
+	const struct vpdma_data_format *vpdma_fmt;
+	int plane = fmt->coplanar ? p_data->vb_part : 0;
+	int field = 0;
+	dma_addr_t dma_addr;
+	u32 flags = 0;
+
+	vpdma_fmt = fmt->vpdma_fmt[plane];
+
+	dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
+	if (!dma_addr) {
+		vpe_err(ctx->dev,
+			"acquiring input buffer(%d) dma_addr failed\n",
+			port);
+		return;
+	}
+
+	if (q_data->flags & Q_DATA_FRAME_1D)
+		flags |= VPDMA_DATA_FRAME_1D;
+	if (q_data->flags & Q_DATA_MODE_TILED)
+		flags |= VPDMA_DATA_MODE_TILED;
+
+	vpdma_add_in_dtd(&ctx->desc_list, q_data->width, q_data->height,
+		c_rect, vpdma_fmt, dma_addr, p_data->channel, field, flags);
+}
+
+/*
+ * Enable the expected IRQ sources
+ */
+static void enable_irqs(struct vpe_ctx *ctx)
+{
+	write_reg(ctx->dev, VPE_INT0_ENABLE0_SET, VPE_INT0_LIST0_COMPLETE);
+	write_reg(ctx->dev, VPE_INT0_ENABLE1_SET, VPE_DS1_UV_ERROR_INT);
+
+	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, true);
+}
+
+static void disable_irqs(struct vpe_ctx *ctx)
+{
+	write_reg(ctx->dev, VPE_INT0_ENABLE0_CLR, 0xffffffff);
+	write_reg(ctx->dev, VPE_INT0_ENABLE1_CLR, 0xffffffff);
+
+	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, false);
+}
+
+/* device_run() - prepares and starts the device
+ *
+ * This function is only called when both the source and destination
+ * buffers are in place.
+ */
+static void device_run(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST];
+
+	ctx->src_vb = v4l2_m2m_src_buf_remove(ctx->m2m_ctx);
+	WARN_ON(ctx->src_vb == NULL);
+	ctx->dst_vb = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx);
+	WARN_ON(ctx->dst_vb == NULL);
+
+	/* config descriptors */
+	if (ctx->dev->loaded_mmrs != ctx->mmr_adb.dma_addr || ctx->load_mmrs) {
+		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->mmr_adb);
+		vpdma_add_cfd_adb(&ctx->desc_list, CFD_MMR_CLIENT, &ctx->mmr_adb);
+		ctx->dev->loaded_mmrs = ctx->mmr_adb.dma_addr;
+		ctx->load_mmrs = false;
+	}
+
+	add_out_dtd(ctx, VPE_PORT_LUMA_OUT);
+	if (d_q_data->fmt->coplanar)
+		add_out_dtd(ctx, VPE_PORT_CHROMA_OUT);
+
+	add_in_dtd(ctx, VPE_PORT_LUMA1_IN);
+	add_in_dtd(ctx, VPE_PORT_CHROMA1_IN);
+
+	/* sync on channel control descriptors for input ports */
+	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA1_IN);
+	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA1_IN);
+
+	/* sync on channel control descriptors for output ports */
+	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA_OUT);
+	if (d_q_data->fmt->coplanar)
+		vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA_OUT);
+
+	enable_irqs(ctx);
+
+	vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->desc_list.buf);
+	vpdma_submit_descs(ctx->dev->vpdma, &ctx->desc_list);
+}
+
+static void ds1_uv_error(struct vpe_ctx *ctx)
+{
+	dev_warn(ctx->dev->v4l2_dev.dev,
+		"received downsampler error interrupt\n");
+}
+
+static irqreturn_t vpe_irq(int irq_vpe, void *data)
+{
+	struct vpe_dev *dev = (struct vpe_dev *)data;
+	struct vpe_ctx *ctx;
+	struct vb2_buffer *s_vb, *d_vb;
+	struct v4l2_buffer *s_buf, *d_buf;
+	unsigned long flags;
+	u32 irqst0, irqst1;
+
+	irqst0 = read_reg(dev, VPE_INT0_STATUS0);
+	if (irqst0) {
+		write_reg(dev, VPE_INT0_STATUS0_CLR, irqst0);
+		vpe_dbg(dev, "INT0_STATUS0 = 0x%08x\n", irqst0);
+	}
+
+	irqst1 = read_reg(dev, VPE_INT0_STATUS1);
+	if (irqst1) {
+		write_reg(dev, VPE_INT0_STATUS1_CLR, irqst1);
+		vpe_dbg(dev, "INT0_STATUS1 = 0x%08x\n", irqst1);
+	}
+
+	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
+	if (!ctx) {
+		vpe_err(dev, "instance released before end of transaction\n");
+		goto handled;
+	}
+
+	if (irqst1 & VPE_DS1_UV_ERROR_INT) {
+		irqst1 &= ~VPE_DS1_UV_ERROR_INT;
+		ds1_uv_error(ctx);
+	}
+
+	if (irqst0) {
+		if (irqst0 & VPE_INT0_LIST0_COMPLETE)
+			vpdma_clear_list_stat(ctx->dev->vpdma);
+
+		irqst0 &= ~(VPE_INT0_LIST0_COMPLETE);
+	}
+
+	if (irqst0 | irqst1) {
+		dev_warn(dev->v4l2_dev.dev, "Unexpected interrupt: "
+			"INT0_STATUS0 = 0x%08x, INT0_STATUS1 = 0x%08x\n",
+			irqst0, irqst1);
+	}
+
+	disable_irqs(ctx);
+
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
+
+	vpdma_reset_desc_list(&ctx->desc_list);
+
+	if (ctx->aborting)
+		goto finished;
+
+	s_vb = ctx->src_vb;
+	d_vb = ctx->dst_vb;
+	s_buf = &s_vb->v4l2_buf;
+	d_buf = &d_vb->v4l2_buf;
+
+	d_buf->timestamp = s_buf->timestamp;
+	if (s_buf->flags & V4L2_BUF_FLAG_TIMECODE) {
+		d_buf->flags |= V4L2_BUF_FLAG_TIMECODE;
+		d_buf->timecode = s_buf->timecode;
+	}
+
+	d_buf->sequence = ctx->sequence;
+
+	ctx->sequence++;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	v4l2_m2m_buf_done(s_vb, VB2_BUF_STATE_DONE);
+	v4l2_m2m_buf_done(d_vb, VB2_BUF_STATE_DONE);
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	ctx->bufs_completed++;
+	if (ctx->bufs_completed < ctx->bufs_per_job) {
+		device_run(ctx);
+		goto handled;
+	}
+
+finished:
+	vpe_dbg(ctx->dev, "finishing transaction\n");
+	ctx->bufs_completed = 0;
+	v4l2_m2m_job_finish(dev->m2m_dev, ctx->m2m_ctx);
+handled:
+	return IRQ_HANDLED;
+}
+
+/*
+ * video ioctls
+ */
+static int vpe_querycap(struct file *file, void *priv,
+			struct v4l2_capability *cap)
+{
+	strncpy(cap->driver, VPE_MODULE_NAME, sizeof(cap->driver) - 1);
+	strncpy(cap->card, VPE_MODULE_NAME, sizeof(cap->card) - 1);
+	strlcpy(cap->bus_info, VPE_MODULE_NAME, sizeof(cap->bus_info));
+	cap->device_caps  = V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int __enum_fmt(struct v4l2_fmtdesc *f, u32 type)
+{
+	int i, index;
+	struct vpe_fmt *fmt = NULL;
+
+	index = 0;
+	for (i = 0; i < ARRAY_SIZE(vpe_formats); ++i) {
+		if (vpe_formats[i].types & type) {
+			if (index == f->index) {
+				fmt = &vpe_formats[i];
+				break;
+			}
+			index++;
+		}
+	}
+
+	if (!fmt)
+		return -EINVAL;
+
+	strncpy(f->description, fmt->name, sizeof(f->description) - 1);
+	f->pixelformat = fmt->fourcc;
+	return 0;
+}
+
+static int vpe_enum_fmt(struct file *file, void *priv,
+				struct v4l2_fmtdesc *f)
+{
+	if (V4L2_TYPE_IS_OUTPUT(f->type))
+		return __enum_fmt(f, VPE_FMT_TYPE_OUTPUT);
+
+	return __enum_fmt(f, VPE_FMT_TYPE_CAPTURE);
+}
+
+static int vpe_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vb2_queue *vq;
+	struct vpe_q_data *q_data;
+	int i;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+
+	pix->width = q_data->width;
+	pix->height = q_data->height;
+	pix->pixelformat = q_data->fmt->fourcc;
+
+	if (V4L2_TYPE_IS_OUTPUT(f->type)) {
+		pix->colorspace = q_data->colorspace;
+	} else {
+		struct vpe_q_data *s_q_data;
+
+		/* get colorspace from the source queue */
+		s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
+
+		pix->colorspace = s_q_data->colorspace;
+	}
+
+	pix->num_planes = q_data->fmt->coplanar ? 2 : 1;
+
+	for (i = 0; i < pix->num_planes; i++) {
+		pix->plane_fmt[i].bytesperline = q_data->bytesperline[i];
+		pix->plane_fmt[i].sizeimage = q_data->sizeimage[i];
+	}
+
+	return 0;
+}
+
+static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
+		       struct vpe_fmt *fmt, int type)
+{
+	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
+	struct v4l2_plane_pix_format *plane_fmt;
+	int i;
+
+	if (!fmt || !(fmt->types & type)) {
+		vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
+			pix->pixelformat);
+		return -EINVAL;
+	}
+
+	pix->field = V4L2_FIELD_NONE;