1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * TI VPE mem2mem driver, based on the virtual v4l2-mem2mem example driver
4 *
5 * Copyright (c) 2013 Texas Instruments Inc.
6 * David Griego, <dagriego@biglakesoftware.com>
7 * Dale Farnsworth, <dale@farnsworth.org>
8 * Archit Taneja, <archit@ti.com>
9 *
10 * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
11 * Pawel Osciak, <pawel@osciak.com>
12 * Marek Szyprowski, <m.szyprowski@samsung.com>
13 *
14 * Based on the virtual v4l2-mem2mem example device
15 */
16
17#include <linux/delay.h>
18#include <linux/dma-mapping.h>
19#include <linux/err.h>
20#include <linux/fs.h>
21#include <linux/interrupt.h>
22#include <linux/io.h>
23#include <linux/ioctl.h>
24#include <linux/module.h>
25#include <linux/of.h>
26#include <linux/platform_device.h>
27#include <linux/pm_runtime.h>
28#include <linux/sched.h>
29#include <linux/slab.h>
30#include <linux/videodev2.h>
31#include <linux/log2.h>
32#include <linux/sizes.h>
33
34#include <media/v4l2-common.h>
35#include <media/v4l2-ctrls.h>
36#include <media/v4l2-device.h>
37#include <media/v4l2-event.h>
38#include <media/v4l2-ioctl.h>
39#include <media/v4l2-mem2mem.h>
40#include <media/videobuf2-v4l2.h>
41#include <media/videobuf2-dma-contig.h>
42
43#include "vpdma.h"
44#include "vpdma_priv.h"
45#include "vpe_regs.h"
46#include "sc.h"
47#include "csc.h"
48
49#define VPE_MODULE_NAME "vpe"
50
51/* minimum and maximum frame sizes */
52#define MIN_W		32
53#define MIN_H		32
54#define MAX_W		2048
55#define MAX_H		2048
56
57/* required alignments */
58#define S_ALIGN		0	/* multiple of 1 */
59#define H_ALIGN		1	/* multiple of 2 */
60
61/* flags that indicate a format can be used for capture/output */
62#define VPE_FMT_TYPE_CAPTURE	(1 << 0)
63#define VPE_FMT_TYPE_OUTPUT	(1 << 1)
64
65/* used as plane indices */
66#define VPE_MAX_PLANES	2
67#define VPE_LUMA	0
68#define VPE_CHROMA	1
69
70/* per m2m context info */
71#define VPE_MAX_SRC_BUFS	3	/* need 3 src fields to de-interlace */
72
73#define VPE_DEF_BUFS_PER_JOB	1	/* default one buffer per batch job */
74
75/*
76 * each VPE context can need up to 3 config descriptors, 7 input descriptors,
77 * 3 output descriptors, and 10 control descriptors
78 */
79#define VPE_DESC_LIST_SIZE	(10 * VPDMA_DTD_DESC_SIZE +	\
80					13 * VPDMA_CFD_CTD_DESC_SIZE)
81
82#define vpe_dbg(vpedev, fmt, arg...)	\
83		dev_dbg((vpedev)->v4l2_dev.dev, fmt, ##arg)
84#define vpe_err(vpedev, fmt, arg...)	\
85		dev_err((vpedev)->v4l2_dev.dev, fmt, ##arg)
86
87struct vpe_us_coeffs {
88	unsigned short	anchor_fid0_c0;
89	unsigned short	anchor_fid0_c1;
90	unsigned short	anchor_fid0_c2;
91	unsigned short	anchor_fid0_c3;
92	unsigned short	interp_fid0_c0;
93	unsigned short	interp_fid0_c1;
94	unsigned short	interp_fid0_c2;
95	unsigned short	interp_fid0_c3;
96	unsigned short	anchor_fid1_c0;
97	unsigned short	anchor_fid1_c1;
98	unsigned short	anchor_fid1_c2;
99	unsigned short	anchor_fid1_c3;
100	unsigned short	interp_fid1_c0;
101	unsigned short	interp_fid1_c1;
102	unsigned short	interp_fid1_c2;
103	unsigned short	interp_fid1_c3;
104};
105
106/*
107 * Default upsampler coefficients
108 */
109static const struct vpe_us_coeffs us_coeffs[] = {
110	{
111		/* Coefficients for progressive input */
112		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
113		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
114	},
115	{
116		/* Coefficients for Top Field Interlaced input */
117		0x0051, 0x03D5, 0x3FE3, 0x3FF7, 0x3FB5, 0x02E9, 0x018F, 0x3FD3,
118		/* Coefficients for Bottom Field Interlaced input */
119		0x016B, 0x0247, 0x00B1, 0x3F9D, 0x3FCF, 0x03DB, 0x005D, 0x3FF9,
120	},
121};
122
123/*
124 * the following registers are for configuring some of the parameters of the
125 * motion and edge detection blocks inside DEI, these generally remain the same,
126 * these could be passed later via userspace if some one needs to tweak these.
127 */
128struct vpe_dei_regs {
129	unsigned long mdt_spacial_freq_thr_reg;		/* VPE_DEI_REG2 */
130	unsigned long edi_config_reg;			/* VPE_DEI_REG3 */
131	unsigned long edi_lut_reg0;			/* VPE_DEI_REG4 */
132	unsigned long edi_lut_reg1;			/* VPE_DEI_REG5 */
133	unsigned long edi_lut_reg2;			/* VPE_DEI_REG6 */
134	unsigned long edi_lut_reg3;			/* VPE_DEI_REG7 */
135};
136
137/*
138 * default expert DEI register values, unlikely to be modified.
139 */
140static const struct vpe_dei_regs dei_regs = {
141	.mdt_spacial_freq_thr_reg = 0x020C0804u,
142	.edi_config_reg = 0x0118100Cu,
143	.edi_lut_reg0 = 0x08040200u,
144	.edi_lut_reg1 = 0x1010100Cu,
145	.edi_lut_reg2 = 0x10101010u,
146	.edi_lut_reg3 = 0x10101010u,
147};
148
149/*
150 * The port_data structure contains per-port data.
151 */
152struct vpe_port_data {
153	enum vpdma_channel channel;	/* VPDMA channel */
154	u8	vb_index;		/* input frame f, f-1, f-2 index */
155	u8	vb_part;		/* plane index for co-panar formats */
156};
157
158/*
159 * Define indices into the port_data tables
160 */
161#define VPE_PORT_LUMA1_IN	0
162#define VPE_PORT_CHROMA1_IN	1
163#define VPE_PORT_LUMA2_IN	2
164#define VPE_PORT_CHROMA2_IN	3
165#define VPE_PORT_LUMA3_IN	4
166#define VPE_PORT_CHROMA3_IN	5
167#define VPE_PORT_MV_IN		6
168#define VPE_PORT_MV_OUT		7
169#define VPE_PORT_LUMA_OUT	8
170#define VPE_PORT_CHROMA_OUT	9
171#define VPE_PORT_RGB_OUT	10
172
173static const struct vpe_port_data port_data[11] = {
174	[VPE_PORT_LUMA1_IN] = {
175		.channel	= VPE_CHAN_LUMA1_IN,
176		.vb_index	= 0,
177		.vb_part	= VPE_LUMA,
178	},
179	[VPE_PORT_CHROMA1_IN] = {
180		.channel	= VPE_CHAN_CHROMA1_IN,
181		.vb_index	= 0,
182		.vb_part	= VPE_CHROMA,
183	},
184	[VPE_PORT_LUMA2_IN] = {
185		.channel	= VPE_CHAN_LUMA2_IN,
186		.vb_index	= 1,
187		.vb_part	= VPE_LUMA,
188	},
189	[VPE_PORT_CHROMA2_IN] = {
190		.channel	= VPE_CHAN_CHROMA2_IN,
191		.vb_index	= 1,
192		.vb_part	= VPE_CHROMA,
193	},
194	[VPE_PORT_LUMA3_IN] = {
195		.channel	= VPE_CHAN_LUMA3_IN,
196		.vb_index	= 2,
197		.vb_part	= VPE_LUMA,
198	},
199	[VPE_PORT_CHROMA3_IN] = {
200		.channel	= VPE_CHAN_CHROMA3_IN,
201		.vb_index	= 2,
202		.vb_part	= VPE_CHROMA,
203	},
204	[VPE_PORT_MV_IN] = {
205		.channel	= VPE_CHAN_MV_IN,
206	},
207	[VPE_PORT_MV_OUT] = {
208		.channel	= VPE_CHAN_MV_OUT,
209	},
210	[VPE_PORT_LUMA_OUT] = {
211		.channel	= VPE_CHAN_LUMA_OUT,
212		.vb_part	= VPE_LUMA,
213	},
214	[VPE_PORT_CHROMA_OUT] = {
215		.channel	= VPE_CHAN_CHROMA_OUT,
216		.vb_part	= VPE_CHROMA,
217	},
218	[VPE_PORT_RGB_OUT] = {
219		.channel	= VPE_CHAN_RGB_OUT,
220		.vb_part	= VPE_LUMA,
221	},
222};
223
224
225/* driver info for each of the supported video formats */
226struct vpe_fmt {
227	u32	fourcc;			/* standard format identifier */
228	u8	types;			/* CAPTURE and/or OUTPUT */
229	u8	coplanar;		/* set for unpacked Luma and Chroma */
230	/* vpdma format info for each plane */
231	struct vpdma_data_format const *vpdma_fmt[VPE_MAX_PLANES];
232};
233
234static struct vpe_fmt vpe_formats[] = {
235	{
236		.fourcc		= V4L2_PIX_FMT_NV16,
237		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
238		.coplanar	= 1,
239		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y444],
240				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C444],
241				  },
242	},
243	{
244		.fourcc		= V4L2_PIX_FMT_NV12,
245		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
246		.coplanar	= 1,
247		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420],
248				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C420],
249				  },
250	},
251	{
252		.fourcc		= V4L2_PIX_FMT_NV21,
253		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
254		.coplanar	= 1,
255		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420],
256				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_CB420],
257				  },
258	},
259	{
260		.fourcc		= V4L2_PIX_FMT_YUYV,
261		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
262		.coplanar	= 0,
263		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_YCB422],
264				  },
265	},
266	{
267		.fourcc		= V4L2_PIX_FMT_UYVY,
268		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
269		.coplanar	= 0,
270		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_CBY422],
271				  },
272	},
273	{
274		.fourcc		= V4L2_PIX_FMT_RGB24,
275		.types		= VPE_FMT_TYPE_CAPTURE,
276		.coplanar	= 0,
277		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGB24],
278				  },
279	},
280	{
281		.fourcc		= V4L2_PIX_FMT_RGB32,
282		.types		= VPE_FMT_TYPE_CAPTURE,
283		.coplanar	= 0,
284		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_ARGB32],
285				  },
286	},
287	{
288		.fourcc		= V4L2_PIX_FMT_BGR24,
289		.types		= VPE_FMT_TYPE_CAPTURE,
290		.coplanar	= 0,
291		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_BGR24],
292				  },
293	},
294	{
295		.fourcc		= V4L2_PIX_FMT_BGR32,
296		.types		= VPE_FMT_TYPE_CAPTURE,
297		.coplanar	= 0,
298		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_ABGR32],
299				  },
300	},
301	{
302		.fourcc		= V4L2_PIX_FMT_RGB565,
303		.types		= VPE_FMT_TYPE_CAPTURE,
304		.coplanar	= 0,
305		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGB565],
306				  },
307	},
308	{
309		.fourcc		= V4L2_PIX_FMT_RGB555,
310		.types		= VPE_FMT_TYPE_CAPTURE,
311		.coplanar	= 0,
312		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGBA16_5551],
313				  },
314	},
315};
316
317/*
318 * per-queue, driver-specific private data.
319 * there is one source queue and one destination queue for each m2m context.
320 */
321struct vpe_q_data {
322	/* current v4l2 format info */
323	struct v4l2_format	format;
324	unsigned int		flags;
325	struct v4l2_rect	c_rect;				/* crop/compose rectangle */
326	struct vpe_fmt		*fmt;				/* format info */
327};
328
329/* vpe_q_data flag bits */
330#define	Q_DATA_FRAME_1D			BIT(0)
331#define	Q_DATA_MODE_TILED		BIT(1)
332#define	Q_DATA_INTERLACED_ALTERNATE	BIT(2)
333#define	Q_DATA_INTERLACED_SEQ_TB	BIT(3)
334#define	Q_DATA_INTERLACED_SEQ_BT	BIT(4)
335
336#define Q_IS_SEQ_XX		(Q_DATA_INTERLACED_SEQ_TB | \
337				Q_DATA_INTERLACED_SEQ_BT)
338
339#define Q_IS_INTERLACED		(Q_DATA_INTERLACED_ALTERNATE | \
340				Q_DATA_INTERLACED_SEQ_TB | \
341				Q_DATA_INTERLACED_SEQ_BT)
342
343enum {
344	Q_DATA_SRC = 0,
345	Q_DATA_DST = 1,
346};
347
348/* find our format description corresponding to the passed v4l2_format */
349static struct vpe_fmt *__find_format(u32 fourcc)
350{
351	struct vpe_fmt *fmt;
352	unsigned int k;
353
354	for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) {
355		fmt = &vpe_formats[k];
356		if (fmt->fourcc == fourcc)
357			return fmt;
358	}
359
360	return NULL;
361}
362
363static struct vpe_fmt *find_format(struct v4l2_format *f)
364{
365	return __find_format(f->fmt.pix.pixelformat);
366}
367
368/*
369 * there is one vpe_dev structure in the driver, it is shared by
370 * all instances.
371 */
372struct vpe_dev {
373	struct v4l2_device	v4l2_dev;
374	struct video_device	vfd;
375	struct v4l2_m2m_dev	*m2m_dev;
376
377	atomic_t		num_instances;	/* count of driver instances */
378	dma_addr_t		loaded_mmrs;	/* shadow mmrs in device */
379	struct mutex		dev_mutex;
380	spinlock_t		lock;
381
382	int			irq;
383	void __iomem		*base;
384	struct resource		*res;
385
386	struct vpdma_data	vpdma_data;
387	struct vpdma_data	*vpdma;		/* vpdma data handle */
388	struct sc_data		*sc;		/* scaler data handle */
389	struct csc_data		*csc;		/* csc data handle */
390};
391
392/*
393 * There is one vpe_ctx structure for each m2m context.
394 */
395struct vpe_ctx {
396	struct v4l2_fh		fh;
397	struct vpe_dev		*dev;
398	struct v4l2_ctrl_handler hdl;
399
400	unsigned int		field;			/* current field */
401	unsigned int		sequence;		/* current frame/field seq */
402	unsigned int		aborting;		/* abort after next irq */
403
404	unsigned int		bufs_per_job;		/* input buffers per batch */
405	unsigned int		bufs_completed;		/* bufs done in this batch */
406
407	struct vpe_q_data	q_data[2];		/* src & dst queue data */
408	struct vb2_v4l2_buffer	*src_vbs[VPE_MAX_SRC_BUFS];
409	struct vb2_v4l2_buffer	*dst_vb;
410
411	dma_addr_t		mv_buf_dma[2];		/* dma addrs of motion vector in/out bufs */
412	void			*mv_buf[2];		/* virtual addrs of motion vector bufs */
413	size_t			mv_buf_size;		/* current motion vector buffer size */
414	struct vpdma_buf	mmr_adb;		/* shadow reg addr/data block */
415	struct vpdma_buf	sc_coeff_h;		/* h coeff buffer */
416	struct vpdma_buf	sc_coeff_v;		/* v coeff buffer */
417	struct vpdma_desc_list	desc_list;		/* DMA descriptor list */
418
419	bool			deinterlacing;		/* using de-interlacer */
420	bool			load_mmrs;		/* have new shadow reg values */
421
422	unsigned int		src_mv_buf_selector;
423};
424
425
426/*
427 * M2M devices get 2 queues.
428 * Return the queue given the type.
429 */
430static struct vpe_q_data *get_q_data(struct vpe_ctx *ctx,
431				     enum v4l2_buf_type type)
432{
433	switch (type) {
434	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
435	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
436		return &ctx->q_data[Q_DATA_SRC];
437	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
438	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
439		return &ctx->q_data[Q_DATA_DST];
440	default:
441		return NULL;
442	}
443	return NULL;
444}
445
446static u32 read_reg(struct vpe_dev *dev, int offset)
447{
448	return ioread32(dev->base + offset);
449}
450
451static void write_reg(struct vpe_dev *dev, int offset, u32 value)
452{
453	iowrite32(value, dev->base + offset);
454}
455
456/* register field read/write helpers */
457static int get_field(u32 value, u32 mask, int shift)
458{
459	return (value & (mask << shift)) >> shift;
460}
461
462static int read_field_reg(struct vpe_dev *dev, int offset, u32 mask, int shift)
463{
464	return get_field(read_reg(dev, offset), mask, shift);
465}
466
467static void write_field(u32 *valp, u32 field, u32 mask, int shift)
468{
469	u32 val = *valp;
470
471	val &= ~(mask << shift);
472	val |= (field & mask) << shift;
473	*valp = val;
474}
475
476static void write_field_reg(struct vpe_dev *dev, int offset, u32 field,
477		u32 mask, int shift)
478{
479	u32 val = read_reg(dev, offset);
480
481	write_field(&val, field, mask, shift);
482
483	write_reg(dev, offset, val);
484}
485
486/*
487 * DMA address/data block for the shadow registers
488 */
489struct vpe_mmr_adb {
490	struct vpdma_adb_hdr	out_fmt_hdr;
491	u32			out_fmt_reg[1];
492	u32			out_fmt_pad[3];
493	struct vpdma_adb_hdr	us1_hdr;
494	u32			us1_regs[8];
495	struct vpdma_adb_hdr	us2_hdr;
496	u32			us2_regs[8];
497	struct vpdma_adb_hdr	us3_hdr;
498	u32			us3_regs[8];
499	struct vpdma_adb_hdr	dei_hdr;
500	u32			dei_regs[8];
501	struct vpdma_adb_hdr	sc_hdr0;
502	u32			sc_regs0[7];
503	u32			sc_pad0[1];
504	struct vpdma_adb_hdr	sc_hdr8;
505	u32			sc_regs8[6];
506	u32			sc_pad8[2];
507	struct vpdma_adb_hdr	sc_hdr17;
508	u32			sc_regs17[9];
509	u32			sc_pad17[3];
510	struct vpdma_adb_hdr	csc_hdr;
511	u32			csc_regs[6];
512	u32			csc_pad[2];
513};
514
515#define GET_OFFSET_TOP(ctx, obj, reg)	\
516	((obj)->res->start - ctx->dev->res->start + reg)
517
518#define VPE_SET_MMR_ADB_HDR(ctx, hdr, regs, offset_a)	\
519	VPDMA_SET_MMR_ADB_HDR(ctx->mmr_adb, vpe_mmr_adb, hdr, regs, offset_a)
520/*
521 * Set the headers for all of the address/data block structures.
522 */
523static void init_adb_hdrs(struct vpe_ctx *ctx)
524{
525	VPE_SET_MMR_ADB_HDR(ctx, out_fmt_hdr, out_fmt_reg, VPE_CLK_FORMAT_SELECT);
526	VPE_SET_MMR_ADB_HDR(ctx, us1_hdr, us1_regs, VPE_US1_R0);
527	VPE_SET_MMR_ADB_HDR(ctx, us2_hdr, us2_regs, VPE_US2_R0);
528	VPE_SET_MMR_ADB_HDR(ctx, us3_hdr, us3_regs, VPE_US3_R0);
529	VPE_SET_MMR_ADB_HDR(ctx, dei_hdr, dei_regs, VPE_DEI_FRAME_SIZE);
530	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr0, sc_regs0,
531		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC0));
532	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr8, sc_regs8,
533		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC8));
534	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr17, sc_regs17,
535		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC17));
536	VPE_SET_MMR_ADB_HDR(ctx, csc_hdr, csc_regs,
537		GET_OFFSET_TOP(ctx, ctx->dev->csc, CSC_CSC00));
538};
539
540/*
541 * Allocate or re-allocate the motion vector DMA buffers
542 * There are two buffers, one for input and one for output.
543 * However, the roles are reversed after each field is processed.
544 * In other words, after each field is processed, the previous
545 * output (dst) MV buffer becomes the new input (src) MV buffer.
546 */
547static int realloc_mv_buffers(struct vpe_ctx *ctx, size_t size)
548{
549	struct device *dev = ctx->dev->v4l2_dev.dev;
550
551	if (ctx->mv_buf_size == size)
552		return 0;
553
554	if (ctx->mv_buf[0])
555		dma_free_coherent(dev, ctx->mv_buf_size, ctx->mv_buf[0],
556			ctx->mv_buf_dma[0]);
557
558	if (ctx->mv_buf[1])
559		dma_free_coherent(dev, ctx->mv_buf_size, ctx->mv_buf[1],
560			ctx->mv_buf_dma[1]);
561
562	if (size == 0)
563		return 0;
564
565	ctx->mv_buf[0] = dma_alloc_coherent(dev, size, &ctx->mv_buf_dma[0],
566				GFP_KERNEL);
567	if (!ctx->mv_buf[0]) {
568		vpe_err(ctx->dev, "failed to allocate motion vector buffer\n");
569		return -ENOMEM;
570	}
571
572	ctx->mv_buf[1] = dma_alloc_coherent(dev, size, &ctx->mv_buf_dma[1],
573				GFP_KERNEL);
574	if (!ctx->mv_buf[1]) {
575		vpe_err(ctx->dev, "failed to allocate motion vector buffer\n");
576		dma_free_coherent(dev, size, ctx->mv_buf[0],
577			ctx->mv_buf_dma[0]);
578
579		return -ENOMEM;
580	}
581
582	ctx->mv_buf_size = size;
583	ctx->src_mv_buf_selector = 0;
584
585	return 0;
586}
587
588static void free_mv_buffers(struct vpe_ctx *ctx)
589{
590	realloc_mv_buffers(ctx, 0);
591}
592
593/*
594 * While de-interlacing, we keep the two most recent input buffers
595 * around.  This function frees those two buffers when we have
596 * finished processing the current stream.
597 */
598static void free_vbs(struct vpe_ctx *ctx)
599{
600	struct vpe_dev *dev = ctx->dev;
601	unsigned long flags;
602
603	if (ctx->src_vbs[2] == NULL)
604		return;
605
606	spin_lock_irqsave(&dev->lock, flags);
607	if (ctx->src_vbs[2]) {
608		v4l2_m2m_buf_done(ctx->src_vbs[2], VB2_BUF_STATE_DONE);
609		if (ctx->src_vbs[1] && (ctx->src_vbs[1] != ctx->src_vbs[2]))
610			v4l2_m2m_buf_done(ctx->src_vbs[1], VB2_BUF_STATE_DONE);
611		ctx->src_vbs[2] = NULL;
612		ctx->src_vbs[1] = NULL;
613	}
614	spin_unlock_irqrestore(&dev->lock, flags);
615}
616
617/*
618 * Enable or disable the VPE clocks
619 */
620static void vpe_set_clock_enable(struct vpe_dev *dev, bool on)
621{
622	u32 val = 0;
623
624	if (on)
625		val = VPE_DATA_PATH_CLK_ENABLE | VPE_VPEDMA_CLK_ENABLE;
626	write_reg(dev, VPE_CLK_ENABLE, val);
627}
628
629static void vpe_top_reset(struct vpe_dev *dev)
630{
631
632	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_DATA_PATH_CLK_RESET_MASK,
633		VPE_DATA_PATH_CLK_RESET_SHIFT);
634
635	usleep_range(100, 150);
636
637	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_DATA_PATH_CLK_RESET_MASK,
638		VPE_DATA_PATH_CLK_RESET_SHIFT);
639}
640
641static void vpe_top_vpdma_reset(struct vpe_dev *dev)
642{
643	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_VPDMA_CLK_RESET_MASK,
644		VPE_VPDMA_CLK_RESET_SHIFT);
645
646	usleep_range(100, 150);
647
648	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_VPDMA_CLK_RESET_MASK,
649		VPE_VPDMA_CLK_RESET_SHIFT);
650}
651
652/*
653 * Load the correct of upsampler coefficients into the shadow MMRs
654 */
655static void set_us_coefficients(struct vpe_ctx *ctx)
656{
657	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
658	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
659	u32 *us1_reg = &mmr_adb->us1_regs[0];
660	u32 *us2_reg = &mmr_adb->us2_regs[0];
661	u32 *us3_reg = &mmr_adb->us3_regs[0];
662	const unsigned short *cp, *end_cp;
663
664	cp = &us_coeffs[0].anchor_fid0_c0;
665
666	if (s_q_data->flags & Q_IS_INTERLACED)		/* interlaced */
667		cp += sizeof(us_coeffs[0]) / sizeof(*cp);
668
669	end_cp = cp + sizeof(us_coeffs[0]) / sizeof(*cp);
670
671	while (cp < end_cp) {
672		write_field(us1_reg, *cp++, VPE_US_C0_MASK, VPE_US_C0_SHIFT);
673		write_field(us1_reg, *cp++, VPE_US_C1_MASK, VPE_US_C1_SHIFT);
674		*us2_reg++ = *us1_reg;
675		*us3_reg++ = *us1_reg++;
676	}
677	ctx->load_mmrs = true;
678}
679
680/*
681 * Set the upsampler config mode and the VPDMA line mode in the shadow MMRs.
682 */
683static void set_cfg_modes(struct vpe_ctx *ctx)
684{
685	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
686	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
687	u32 *us1_reg0 = &mmr_adb->us1_regs[0];
688	u32 *us2_reg0 = &mmr_adb->us2_regs[0];
689	u32 *us3_reg0 = &mmr_adb->us3_regs[0];
690	int cfg_mode = 1;
691
692	/*
693	 * Cfg Mode 0: YUV420 source, enable upsampler, DEI is de-interlacing.
694	 * Cfg Mode 1: YUV422 source, disable upsampler, DEI is de-interlacing.
695	 */
696
697	if (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
698	    fmt->fourcc == V4L2_PIX_FMT_NV21)
699		cfg_mode = 0;
700
701	write_field(us1_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
702	write_field(us2_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
703	write_field(us3_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
704
705	ctx->load_mmrs = true;
706}
707
708static void set_line_modes(struct vpe_ctx *ctx)
709{
710	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
711	int line_mode = 1;
712
713	if (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
714	    fmt->fourcc == V4L2_PIX_FMT_NV21)
715		line_mode = 0;		/* double lines to line buffer */
716
717	/* regs for now */
718	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA1_IN);
719	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA2_IN);
720	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA3_IN);
721
722	/* frame start for input luma */
723	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
724		VPE_CHAN_LUMA1_IN);
725	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
726		VPE_CHAN_LUMA2_IN);
727	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
728		VPE_CHAN_LUMA3_IN);
729
730	/* frame start for input chroma */
731	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
732		VPE_CHAN_CHROMA1_IN);
733	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
734		VPE_CHAN_CHROMA2_IN);
735	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
736		VPE_CHAN_CHROMA3_IN);
737
738	/* frame start for MV in client */
739	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
740		VPE_CHAN_MV_IN);
741}
742
743/*
744 * Set the shadow registers that are modified when the source
745 * format changes.
746 */
747static void set_src_registers(struct vpe_ctx *ctx)
748{
749	set_us_coefficients(ctx);
750}
751
752/*
753 * Set the shadow registers that are modified when the destination
754 * format changes.
755 */
756static void set_dst_registers(struct vpe_ctx *ctx)
757{
758	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
759	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_DST].fmt;
760	const struct v4l2_format_info *finfo;
761	u32 val = 0;
762
763	finfo = v4l2_format_info(fmt->fourcc);
764	if (v4l2_is_format_rgb(finfo)) {
765		val |= VPE_RGB_OUT_SELECT;
766		vpdma_set_bg_color(ctx->dev->vpdma,
767			(struct vpdma_data_format *)fmt->vpdma_fmt[0], 0xff);
768	} else if (fmt->fourcc == V4L2_PIX_FMT_NV16)
769		val |= VPE_COLOR_SEPARATE_422;
770
771	/*
772	 * the source of CHR_DS and CSC is always the scaler, irrespective of
773	 * whether it's used or not
774	 */
775	val |= VPE_DS_SRC_DEI_SCALER | VPE_CSC_SRC_DEI_SCALER;
776
777	if (fmt->fourcc != V4L2_PIX_FMT_NV12 &&
778	    fmt->fourcc != V4L2_PIX_FMT_NV21)
779		val |= VPE_DS_BYPASS;
780
781	mmr_adb->out_fmt_reg[0] = val;
782
783	ctx->load_mmrs = true;
784}
785
786/*
787 * Set the de-interlacer shadow register values
788 */
789static void set_dei_regs(struct vpe_ctx *ctx)
790{
791	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
792	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
793	unsigned int src_h = s_q_data->c_rect.height;
794	unsigned int src_w = s_q_data->c_rect.width;
795	u32 *dei_mmr0 = &mmr_adb->dei_regs[0];
796	bool deinterlace = true;
797	u32 val = 0;
798
799	/*
800	 * according to TRM, we should set DEI in progressive bypass mode when
801	 * the input content is progressive, however, DEI is bypassed correctly
802	 * for both progressive and interlace content in interlace bypass mode.
803	 * It has been recommended not to use progressive bypass mode.
804	 */
805	if (!(s_q_data->flags & Q_IS_INTERLACED) || !ctx->deinterlacing) {
806		deinterlace = false;
807		val = VPE_DEI_INTERLACE_BYPASS;
808	}
809
810	src_h = deinterlace ? src_h * 2 : src_h;
811
812	val |= (src_h << VPE_DEI_HEIGHT_SHIFT) |
813		(src_w << VPE_DEI_WIDTH_SHIFT) |
814		VPE_DEI_FIELD_FLUSH;
815
816	*dei_mmr0 = val;
817
818	ctx->load_mmrs = true;
819}
820
821static void set_dei_shadow_registers(struct vpe_ctx *ctx)
822{
823	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
824	u32 *dei_mmr = &mmr_adb->dei_regs[0];
825	const struct vpe_dei_regs *cur = &dei_regs;
826
827	dei_mmr[2]  = cur->mdt_spacial_freq_thr_reg;
828	dei_mmr[3]  = cur->edi_config_reg;
829	dei_mmr[4]  = cur->edi_lut_reg0;
830	dei_mmr[5]  = cur->edi_lut_reg1;
831	dei_mmr[6]  = cur->edi_lut_reg2;
832	dei_mmr[7]  = cur->edi_lut_reg3;
833
834	ctx->load_mmrs = true;
835}
836
837static void config_edi_input_mode(struct vpe_ctx *ctx, int mode)
838{
839	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
840	u32 *edi_config_reg = &mmr_adb->dei_regs[3];
841
842	if (mode & 0x2)
843		write_field(edi_config_reg, 1, 1, 2);	/* EDI_ENABLE_3D */
844
845	if (mode & 0x3)
846		write_field(edi_config_reg, 1, 1, 3);	/* EDI_CHROMA_3D  */
847
848	write_field(edi_config_reg, mode, VPE_EDI_INP_MODE_MASK,
849		VPE_EDI_INP_MODE_SHIFT);
850
851	ctx->load_mmrs = true;
852}
853
854/*
855 * Set the shadow registers whose values are modified when either the
856 * source or destination format is changed.
857 */
858static int set_srcdst_params(struct vpe_ctx *ctx)
859{
860	struct vpe_q_data *s_q_data =  &ctx->q_data[Q_DATA_SRC];
861	struct vpe_q_data *d_q_data =  &ctx->q_data[Q_DATA_DST];
862	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
863	unsigned int src_w = s_q_data->c_rect.width;
864	unsigned int src_h = s_q_data->c_rect.height;
865	unsigned int dst_w = d_q_data->c_rect.width;
866	unsigned int dst_h = d_q_data->c_rect.height;
867	struct v4l2_pix_format_mplane *spix;
868	size_t mv_buf_size;
869	int ret;
870
871	ctx->sequence = 0;
872	ctx->field = V4L2_FIELD_TOP;
873	spix = &s_q_data->format.fmt.pix_mp;
874
875	if ((s_q_data->flags & Q_IS_INTERLACED) &&
876			!(d_q_data->flags & Q_IS_INTERLACED)) {
877		int bytes_per_line;
878		const struct vpdma_data_format *mv =
879			&vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
880
881		/*
882		 * we make sure that the source image has a 16 byte aligned
883		 * stride, we need to do the same for the motion vector buffer
884		 * by aligning it's stride to the next 16 byte boundary. this
885		 * extra space will not be used by the de-interlacer, but will
886		 * ensure that vpdma operates correctly
887		 */
888		bytes_per_line = ALIGN((spix->width * mv->depth) >> 3,
889				       VPDMA_STRIDE_ALIGN);
890		mv_buf_size = bytes_per_line * spix->height;
891
892		ctx->deinterlacing = true;
893		src_h <<= 1;
894	} else {
895		ctx->deinterlacing = false;
896		mv_buf_size = 0;
897	}
898
899	free_vbs(ctx);
900	ctx->src_vbs[2] = ctx->src_vbs[1] = ctx->src_vbs[0] = NULL;
901
902	ret = realloc_mv_buffers(ctx, mv_buf_size);
903	if (ret)
904		return ret;
905
906	set_cfg_modes(ctx);
907	set_dei_regs(ctx);
908
909	csc_set_coeff(ctx->dev->csc, &mmr_adb->csc_regs[0],
910		      &s_q_data->format, &d_q_data->format);
911
912	sc_set_hs_coeffs(ctx->dev->sc, ctx->sc_coeff_h.addr, src_w, dst_w);
913	sc_set_vs_coeffs(ctx->dev->sc, ctx->sc_coeff_v.addr, src_h, dst_h);
914
915	sc_config_scaler(ctx->dev->sc, &mmr_adb->sc_regs0[0],
916		&mmr_adb->sc_regs8[0], &mmr_adb->sc_regs17[0],
917		src_w, src_h, dst_w, dst_h);
918
919	return 0;
920}
921
922/*
923 * mem2mem callbacks
924 */
925
926/*
927 * job_ready() - check whether an instance is ready to be scheduled to run
928 */
929static int job_ready(void *priv)
930{
931	struct vpe_ctx *ctx = priv;
932
933	/*
934	 * This check is needed as this might be called directly from driver
935	 * When called by m2m framework, this will always satisfy, but when
936	 * called from vpe_irq, this might fail. (src stream with zero buffers)
937	 */
938	if (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) <= 0 ||
939		v4l2_m2m_num_dst_bufs_ready(ctx->fh.m2m_ctx) <= 0)
940		return 0;
941
942	return 1;
943}
944
945static void job_abort(void *priv)
946{
947	struct vpe_ctx *ctx = priv;
948
949	/* Will cancel the transaction in the next interrupt handler */
950	ctx->aborting = 1;
951}
952
953static void vpe_dump_regs(struct vpe_dev *dev)
954{
955#define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r))
956
957	vpe_dbg(dev, "VPE Registers:\n");
958
959	DUMPREG(PID);
960	DUMPREG(SYSCONFIG);
961	DUMPREG(INT0_STATUS0_RAW);
962	DUMPREG(INT0_STATUS0);
963	DUMPREG(INT0_ENABLE0);
964	DUMPREG(INT0_STATUS1_RAW);
965	DUMPREG(INT0_STATUS1);
966	DUMPREG(INT0_ENABLE1);
967	DUMPREG(CLK_ENABLE);
968	DUMPREG(CLK_RESET);
969	DUMPREG(CLK_FORMAT_SELECT);
970	DUMPREG(CLK_RANGE_MAP);
971	DUMPREG(US1_R0);
972	DUMPREG(US1_R1);
973	DUMPREG(US1_R2);
974	DUMPREG(US1_R3);
975	DUMPREG(US1_R4);
976	DUMPREG(US1_R5);
977	DUMPREG(US1_R6);
978	DUMPREG(US1_R7);
979	DUMPREG(US2_R0);
980	DUMPREG(US2_R1);
981	DUMPREG(US2_R2);
982	DUMPREG(US2_R3);
983	DUMPREG(US2_R4);
984	DUMPREG(US2_R5);
985	DUMPREG(US2_R6);
986	DUMPREG(US2_R7);
987	DUMPREG(US3_R0);
988	DUMPREG(US3_R1);
989	DUMPREG(US3_R2);
990	DUMPREG(US3_R3);
991	DUMPREG(US3_R4);
992	DUMPREG(US3_R5);
993	DUMPREG(US3_R6);
994	DUMPREG(US3_R7);
995	DUMPREG(DEI_FRAME_SIZE);
996	DUMPREG(MDT_BYPASS);
997	DUMPREG(MDT_SF_THRESHOLD);
998	DUMPREG(EDI_CONFIG);
999	DUMPREG(DEI_EDI_LUT_R0);
1000	DUMPREG(DEI_EDI_LUT_R1);
1001	DUMPREG(DEI_EDI_LUT_R2);
1002	DUMPREG(DEI_EDI_LUT_R3);
1003	DUMPREG(DEI_FMD_WINDOW_R0);
1004	DUMPREG(DEI_FMD_WINDOW_R1);
1005	DUMPREG(DEI_FMD_CONTROL_R0);
1006	DUMPREG(DEI_FMD_CONTROL_R1);
1007	DUMPREG(DEI_FMD_STATUS_R0);
1008	DUMPREG(DEI_FMD_STATUS_R1);
1009	DUMPREG(DEI_FMD_STATUS_R2);
1010#undef DUMPREG
1011
1012	sc_dump_regs(dev->sc);
1013	csc_dump_regs(dev->csc);
1014}
1015
1016static void add_out_dtd(struct vpe_ctx *ctx, int port)
1017{
1018	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_DST];
1019	const struct vpe_port_data *p_data = &port_data[port];
1020	struct vb2_buffer *vb = &ctx->dst_vb->vb2_buf;
1021	struct vpe_fmt *fmt = q_data->fmt;
1022	const struct vpdma_data_format *vpdma_fmt;
1023	int mv_buf_selector = !ctx->src_mv_buf_selector;
1024	struct v4l2_pix_format_mplane *pix;
1025	dma_addr_t dma_addr;
1026	u32 flags = 0;
1027	u32 offset = 0;
1028	u32 stride;
1029
1030	if (port == VPE_PORT_MV_OUT) {
1031		vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
1032		dma_addr = ctx->mv_buf_dma[mv_buf_selector];
1033		q_data = &ctx->q_data[Q_DATA_SRC];
1034		pix = &q_data->format.fmt.pix_mp;
1035		stride = ALIGN((pix->width * vpdma_fmt->depth) >> 3,
1036			       VPDMA_STRIDE_ALIGN);
1037	} else {
1038		/* to incorporate interleaved formats */
1039		int plane = fmt->coplanar ? p_data->vb_part : 0;
1040
1041		pix = &q_data->format.fmt.pix_mp;
1042		vpdma_fmt = fmt->vpdma_fmt[plane];
1043		/*
1044		 * If we are using a single plane buffer and
1045		 * we need to set a separate vpdma chroma channel.
1046		 */
1047		if (pix->num_planes == 1 && plane) {
1048			dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
1049			/* Compute required offset */
1050			offset = pix->plane_fmt[0].bytesperline * pix->height;
1051		} else {
1052			dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
1053			/* Use address as is, no offset */
1054			offset = 0;
1055		}
1056		if (!dma_addr) {
1057			vpe_err(ctx->dev,
1058				"acquiring output buffer(%d) dma_addr failed\n",
1059				port);
1060			return;
1061		}
1062		/* Apply the offset */
1063		dma_addr += offset;
1064		stride = pix->plane_fmt[VPE_LUMA].bytesperline;
1065	}
1066
1067	if (q_data->flags & Q_DATA_FRAME_1D)
1068		flags |= VPDMA_DATA_FRAME_1D;
1069	if (q_data->flags & Q_DATA_MODE_TILED)
1070		flags |= VPDMA_DATA_MODE_TILED;
1071
1072	vpdma_set_max_size(ctx->dev->vpdma, VPDMA_MAX_SIZE1,
1073			   MAX_W, MAX_H);
1074
1075	vpdma_add_out_dtd(&ctx->desc_list, pix->width,
1076			  stride, &q_data->c_rect,
1077			  vpdma_fmt, dma_addr, MAX_OUT_WIDTH_REG1,
1078			  MAX_OUT_HEIGHT_REG1, p_data->channel, flags);
1079}
1080
1081static void add_in_dtd(struct vpe_ctx *ctx, int port)
1082{
1083	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_SRC];
1084	const struct vpe_port_data *p_data = &port_data[port];
1085	struct vb2_buffer *vb = &ctx->src_vbs[p_data->vb_index]->vb2_buf;
1086	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
1087	struct vpe_fmt *fmt = q_data->fmt;
1088	struct v4l2_pix_format_mplane *pix;
1089	const struct vpdma_data_format *vpdma_fmt;
1090	int mv_buf_selector = ctx->src_mv_buf_selector;
1091	int field = vbuf->field == V4L2_FIELD_BOTTOM;
1092	int frame_width, frame_height;
1093	dma_addr_t dma_addr;
1094	u32 flags = 0;
1095	u32 offset = 0;
1096	u32 stride;
1097
1098	pix = &q_data->format.fmt.pix_mp;
1099	if (port == VPE_PORT_MV_IN) {
1100		vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
1101		dma_addr = ctx->mv_buf_dma[mv_buf_selector];
1102		stride = ALIGN((pix->width * vpdma_fmt->depth) >> 3,
1103			       VPDMA_STRIDE_ALIGN);
1104	} else {
1105		/* to incorporate interleaved formats */
1106		int plane = fmt->coplanar ? p_data->vb_part : 0;
1107
1108		vpdma_fmt = fmt->vpdma_fmt[plane];
1109		/*
1110		 * If we are using a single plane buffer and
1111		 * we need to set a separate vpdma chroma channel.
1112		 */
1113		if (pix->num_planes == 1 && plane) {
1114			dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
1115			/* Compute required offset */
1116			offset = pix->plane_fmt[0].bytesperline * pix->height;
1117		} else {
1118			dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
1119			/* Use address as is, no offset */
1120			offset = 0;
1121		}
1122		if (!dma_addr) {
1123			vpe_err(ctx->dev,
1124				"acquiring output buffer(%d) dma_addr failed\n",
1125				port);
1126			return;
1127		}
1128		/* Apply the offset */
1129		dma_addr += offset;
1130		stride = pix->plane_fmt[VPE_LUMA].bytesperline;
1131
1132		/*
1133		 * field used in VPDMA desc  = 0 (top) / 1 (bottom)
1134		 * Use top or bottom field from same vb alternately
1135		 * For each de-interlacing operation, f,f-1,f-2 should be one
1136		 * of TBT or BTB
1137		 */
1138		if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB ||
1139		    q_data->flags & Q_DATA_INTERLACED_SEQ_BT) {
1140			/* Select initial value based on format */
1141			if (q_data->flags & Q_DATA_INTERLACED_SEQ_BT)
1142				field = 1;
1143			else
1144				field = 0;
1145
1146			/* Toggle for each vb_index and each operation */
1147			field = (field + p_data->vb_index + ctx->sequence) % 2;
1148
1149			if (field) {
1150				int height = pix->height / 2;
1151				int bpp;
1152
1153				if (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
1154				    fmt->fourcc == V4L2_PIX_FMT_NV21)
1155					bpp = 1;
1156				else
1157					bpp = vpdma_fmt->depth >> 3;
1158
1159				if (plane)
1160					height /= 2;
1161
1162				dma_addr += pix->width * height * bpp;
1163			}
1164		}
1165	}
1166
1167	if (q_data->flags & Q_DATA_FRAME_1D)
1168		flags |= VPDMA_DATA_FRAME_1D;
1169	if (q_data->flags & Q_DATA_MODE_TILED)
1170		flags |= VPDMA_DATA_MODE_TILED;
1171
1172	frame_width = q_data->c_rect.width;
1173	frame_height = q_data->c_rect.height;
1174
1175	if (p_data->vb_part && (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
1176				fmt->fourcc == V4L2_PIX_FMT_NV21))
1177		frame_height /= 2;
1178
1179	vpdma_add_in_dtd(&ctx->desc_list, pix->width, stride,
1180			 &q_data->c_rect, vpdma_fmt, dma_addr,
1181			 p_data->channel, field, flags, frame_width,
1182			 frame_height, 0, 0);
1183}
1184
1185/*
1186 * Enable the expected IRQ sources
1187 */
1188static void enable_irqs(struct vpe_ctx *ctx)
1189{
1190	write_reg(ctx->dev, VPE_INT0_ENABLE0_SET, VPE_INT0_LIST0_COMPLETE);
1191	write_reg(ctx->dev, VPE_INT0_ENABLE1_SET, VPE_DEI_ERROR_INT |
1192				VPE_DS1_UV_ERROR_INT);
1193
1194	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, 0, true);
1195}
1196
1197static void disable_irqs(struct vpe_ctx *ctx)
1198{
1199	write_reg(ctx->dev, VPE_INT0_ENABLE0_CLR, 0xffffffff);
1200	write_reg(ctx->dev, VPE_INT0_ENABLE1_CLR, 0xffffffff);
1201
1202	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, 0, false);
1203}
1204
1205/* device_run() - prepares and starts the device
1206 *
1207 * This function is only called when both the source and destination
1208 * buffers are in place.
1209 */
1210static void device_run(void *priv)
1211{
1212	struct vpe_ctx *ctx = priv;
1213	struct sc_data *sc = ctx->dev->sc;
1214	struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST];
1215	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
1216	const struct v4l2_format_info *d_finfo;
1217
1218	d_finfo = v4l2_format_info(d_q_data->fmt->fourcc);
1219
1220	if (ctx->deinterlacing && s_q_data->flags & Q_IS_SEQ_XX &&
1221	    ctx->sequence % 2 == 0) {
1222		/* When using SEQ_XX type buffers, each buffer has two fields
1223		 * each buffer has two fields (top & bottom)
1224		 * Removing one buffer is actually getting two fields
1225		 * Alternate between two operations:-
1226		 * Even : consume one field but DO NOT REMOVE from queue
1227		 * Odd : consume other field and REMOVE from queue
1228		 */
1229		ctx->src_vbs[0] = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
1230		WARN_ON(ctx->src_vbs[0] == NULL);
1231	} else {
1232		ctx->src_vbs[0] = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
1233		WARN_ON(ctx->src_vbs[0] == NULL);
1234	}
1235
1236	ctx->dst_vb = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
1237	WARN_ON(ctx->dst_vb == NULL);
1238
1239	if (ctx->deinterlacing) {
1240
1241		if (ctx->src_vbs[2] == NULL) {
1242			ctx->src_vbs[2] = ctx->src_vbs[0];
1243			WARN_ON(ctx->src_vbs[2] == NULL);
1244			ctx->src_vbs[1] = ctx->src_vbs[0];
1245			WARN_ON(ctx->src_vbs[1] == NULL);
1246		}
1247
1248		/*
1249		 * we have output the first 2 frames through line average, we
1250		 * now switch to EDI de-interlacer
1251		 */
1252		if (ctx->sequence == 2)
1253			config_edi_input_mode(ctx, 0x3); /* EDI (Y + UV) */
1254	}
1255
1256	/* config descriptors */
1257	if (ctx->dev->loaded_mmrs != ctx->mmr_adb.dma_addr || ctx->load_mmrs) {
1258		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->mmr_adb);
1259		vpdma_add_cfd_adb(&ctx->desc_list, CFD_MMR_CLIENT, &ctx->mmr_adb);
1260
1261		set_line_modes(ctx);
1262
1263		ctx->dev->loaded_mmrs = ctx->mmr_adb.dma_addr;
1264		ctx->load_mmrs = false;
1265	}
1266
1267	if (sc->loaded_coeff_h != ctx->sc_coeff_h.dma_addr ||
1268			sc->load_coeff_h) {
1269		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->sc_coeff_h);
1270		vpdma_add_cfd_block(&ctx->desc_list, CFD_SC_CLIENT,
1271			&ctx->sc_coeff_h, 0);
1272
1273		sc->loaded_coeff_h = ctx->sc_coeff_h.dma_addr;
1274		sc->load_coeff_h = false;
1275	}
1276
1277	if (sc->loaded_coeff_v != ctx->sc_coeff_v.dma_addr ||
1278			sc->load_coeff_v) {
1279		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->sc_coeff_v);
1280		vpdma_add_cfd_block(&ctx->desc_list, CFD_SC_CLIENT,
1281			&ctx->sc_coeff_v, SC_COEF_SRAM_SIZE >> 4);
1282
1283		sc->loaded_coeff_v = ctx->sc_coeff_v.dma_addr;
1284		sc->load_coeff_v = false;
1285	}
1286
1287	/* output data descriptors */
1288	if (ctx->deinterlacing)
1289		add_out_dtd(ctx, VPE_PORT_MV_OUT);
1290
1291	if (v4l2_is_format_rgb(d_finfo)) {
1292		add_out_dtd(ctx, VPE_PORT_RGB_OUT);
1293	} else {
1294		add_out_dtd(ctx, VPE_PORT_LUMA_OUT);
1295		if (d_q_data->fmt->coplanar)
1296			add_out_dtd(ctx, VPE_PORT_CHROMA_OUT);
1297	}
1298
1299	/* input data descriptors */
1300	if (ctx->deinterlacing) {
1301		add_in_dtd(ctx, VPE_PORT_LUMA3_IN);
1302		add_in_dtd(ctx, VPE_PORT_CHROMA3_IN);
1303
1304		add_in_dtd(ctx, VPE_PORT_LUMA2_IN);
1305		add_in_dtd(ctx, VPE_PORT_CHROMA2_IN);
1306	}
1307
1308	add_in_dtd(ctx, VPE_PORT_LUMA1_IN);
1309	add_in_dtd(ctx, VPE_PORT_CHROMA1_IN);
1310
1311	if (ctx->deinterlacing)
1312		add_in_dtd(ctx, VPE_PORT_MV_IN);
1313
1314	/* sync on channel control descriptors for input ports */
1315	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA1_IN);
1316	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA1_IN);
1317
1318	if (ctx->deinterlacing) {
1319		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1320			VPE_CHAN_LUMA2_IN);
1321		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1322			VPE_CHAN_CHROMA2_IN);
1323
1324		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1325			VPE_CHAN_LUMA3_IN);
1326		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1327			VPE_CHAN_CHROMA3_IN);
1328
1329		vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_MV_IN);
1330	}
1331
1332	/* sync on channel control descriptors for output ports */
1333	if (v4l2_is_format_rgb(d_finfo)) {
1334		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1335			VPE_CHAN_RGB_OUT);
1336	} else {
1337		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1338			VPE_CHAN_LUMA_OUT);
1339		if (d_q_data->fmt->coplanar)
1340			vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
1341				VPE_CHAN_CHROMA_OUT);
1342	}
1343
1344	if (ctx->deinterlacing)
1345		vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_MV_OUT);
1346
1347	enable_irqs(ctx);
1348
1349	vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->desc_list.buf);
1350	vpdma_submit_descs(ctx->dev->vpdma, &ctx->desc_list, 0);
1351}
1352
1353static void dei_error(struct vpe_ctx *ctx)
1354{
1355	dev_warn(ctx->dev->v4l2_dev.dev,
1356		"received DEI error interrupt\n");
1357}
1358
1359static void ds1_uv_error(struct vpe_ctx *ctx)
1360{
1361	dev_warn(ctx->dev->v4l2_dev.dev,
1362		"received downsampler error interrupt\n");
1363}
1364
1365static irqreturn_t vpe_irq(int irq_vpe, void *data)
1366{
1367	struct vpe_dev *dev = (struct vpe_dev *)data;
1368	struct vpe_ctx *ctx;
1369	struct vpe_q_data *d_q_data;
1370	struct vb2_v4l2_buffer *s_vb, *d_vb;
1371	unsigned long flags;
1372	u32 irqst0, irqst1;
1373	bool list_complete = false;
1374
1375	irqst0 = read_reg(dev, VPE_INT0_STATUS0);
1376	if (irqst0) {
1377		write_reg(dev, VPE_INT0_STATUS0_CLR, irqst0);
1378		vpe_dbg(dev, "INT0_STATUS0 = 0x%08x\n", irqst0);
1379	}
1380
1381	irqst1 = read_reg(dev, VPE_INT0_STATUS1);
1382	if (irqst1) {
1383		write_reg(dev, VPE_INT0_STATUS1_CLR, irqst1);
1384		vpe_dbg(dev, "INT0_STATUS1 = 0x%08x\n", irqst1);
1385	}
1386
1387	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
1388	if (!ctx) {
1389		vpe_err(dev, "instance released before end of transaction\n");
1390		goto handled;
1391	}
1392
1393	if (irqst1) {
1394		if (irqst1 & VPE_DEI_ERROR_INT) {
1395			irqst1 &= ~VPE_DEI_ERROR_INT;
1396			dei_error(ctx);
1397		}
1398		if (irqst1 & VPE_DS1_UV_ERROR_INT) {
1399			irqst1 &= ~VPE_DS1_UV_ERROR_INT;
1400			ds1_uv_error(ctx);
1401		}
1402	}
1403
1404	if (irqst0) {
1405		if (irqst0 & VPE_INT0_LIST0_COMPLETE)
1406			vpdma_clear_list_stat(ctx->dev->vpdma, 0, 0);
1407
1408		irqst0 &= ~(VPE_INT0_LIST0_COMPLETE);
1409		list_complete = true;
1410	}
1411
1412	if (irqst0 | irqst1) {
1413		dev_warn(dev->v4l2_dev.dev, "Unexpected interrupt: INT0_STATUS0 = 0x%08x, INT0_STATUS1 = 0x%08x\n",
1414			irqst0, irqst1);
1415	}
1416
1417	/*
1418	 * Setup next operation only when list complete IRQ occurs
1419	 * otherwise, skip the following code
1420	 */
1421	if (!list_complete)
1422		goto handled;
1423
1424	disable_irqs(ctx);
1425
1426	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
1427	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
1428	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_h);
1429	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_v);
1430
1431	vpdma_reset_desc_list(&ctx->desc_list);
1432
1433	 /* the previous dst mv buffer becomes the next src mv buffer */
1434	ctx->src_mv_buf_selector = !ctx->src_mv_buf_selector;
1435
1436	s_vb = ctx->src_vbs[0];
1437	d_vb = ctx->dst_vb;
1438
1439	d_vb->flags = s_vb->flags;
1440	d_vb->vb2_buf.timestamp = s_vb->vb2_buf.timestamp;
1441
1442	if (s_vb->flags & V4L2_BUF_FLAG_TIMECODE)
1443		d_vb->timecode = s_vb->timecode;
1444
1445	d_vb->sequence = ctx->sequence;
1446	s_vb->sequence = ctx->sequence;
1447
1448	d_q_data = &ctx->q_data[Q_DATA_DST];
1449	if (d_q_data->flags & Q_IS_INTERLACED) {
1450		d_vb->field = ctx->field;
1451		if (ctx->field == V4L2_FIELD_BOTTOM) {
1452			ctx->sequence++;
1453			ctx->field = V4L2_FIELD_TOP;
1454		} else {
1455			WARN_ON(ctx->field != V4L2_FIELD_TOP);
1456			ctx->field = V4L2_FIELD_BOTTOM;
1457		}
1458	} else {
1459		d_vb->field = V4L2_FIELD_NONE;
1460		ctx->sequence++;
1461	}
1462
1463	if (ctx->deinterlacing) {
1464		/*
1465		 * Allow source buffer to be dequeued only if it won't be used
1466		 * in the next iteration. All vbs are initialized to first
1467		 * buffer and we are shifting buffers every iteration, for the
1468		 * first two iterations, no buffer will be dequeued.
1469		 * This ensures that driver will keep (n-2)th (n-1)th and (n)th
1470		 * field when deinterlacing is enabled
1471		 */
1472		if (ctx->src_vbs[2] != ctx->src_vbs[1])
1473			s_vb = ctx->src_vbs[2];
1474		else
1475			s_vb = NULL;
1476	}
1477
1478	spin_lock_irqsave(&dev->lock, flags);
1479
1480	if (s_vb)
1481		v4l2_m2m_buf_done(s_vb, VB2_BUF_STATE_DONE);
1482
1483	v4l2_m2m_buf_done(d_vb, VB2_BUF_STATE_DONE);
1484
1485	spin_unlock_irqrestore(&dev->lock, flags);
1486
1487	if (ctx->deinterlacing) {
1488		ctx->src_vbs[2] = ctx->src_vbs[1];
1489		ctx->src_vbs[1] = ctx->src_vbs[0];
1490	}
1491
1492	/*
1493	 * Since the vb2_buf_done has already been called fir therse
1494	 * buffer we can now NULL them out so that we won't try
1495	 * to clean out stray pointer later on.
1496	*/
1497	ctx->src_vbs[0] = NULL;
1498	ctx->dst_vb = NULL;
1499
1500	if (ctx->aborting)
1501		goto finished;
1502
1503	ctx->bufs_completed++;
1504	if (ctx->bufs_completed < ctx->bufs_per_job && job_ready(ctx)) {
1505		device_run(ctx);
1506		goto handled;
1507	}
1508
1509finished:
1510	vpe_dbg(ctx->dev, "finishing transaction\n");
1511	ctx->bufs_completed = 0;
1512	v4l2_m2m_job_finish(dev->m2m_dev, ctx->fh.m2m_ctx);
1513handled:
1514	return IRQ_HANDLED;
1515}
1516
1517/*
1518 * video ioctls
1519 */
1520static int vpe_querycap(struct file *file, void *priv,
1521			struct v4l2_capability *cap)
1522{
1523	strscpy(cap->driver, VPE_MODULE_NAME, sizeof(cap->driver));
1524	strscpy(cap->card, VPE_MODULE_NAME, sizeof(cap->card));
1525	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
1526		VPE_MODULE_NAME);
1527	return 0;
1528}
1529
1530static int __enum_fmt(struct v4l2_fmtdesc *f, u32 type)
1531{
1532	int i, index;
1533	struct vpe_fmt *fmt = NULL;
1534
1535	index = 0;
1536	for (i = 0; i < ARRAY_SIZE(vpe_formats); ++i) {
1537		if (vpe_formats[i].types & type) {
1538			if (index == f->index) {
1539				fmt = &vpe_formats[i];
1540				break;
1541			}
1542			index++;
1543		}
1544	}
1545
1546	if (!fmt)
1547		return -EINVAL;
1548
1549	f->pixelformat = fmt->fourcc;
1550	return 0;
1551}
1552
1553static int vpe_enum_fmt(struct file *file, void *priv,
1554				struct v4l2_fmtdesc *f)
1555{
1556	if (V4L2_TYPE_IS_OUTPUT(f->type))
1557		return __enum_fmt(f, VPE_FMT_TYPE_OUTPUT);
1558
1559	return __enum_fmt(f, VPE_FMT_TYPE_CAPTURE);
1560}
1561
1562static int vpe_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
1563{
1564	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
1565	struct vpe_ctx *ctx = file->private_data;
1566	struct vb2_queue *vq;
1567	struct vpe_q_data *q_data;
1568
1569	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
1570	if (!vq)
1571		return -EINVAL;
1572
1573	q_data = get_q_data(ctx, f->type);
1574	if (!q_data)
1575		return -EINVAL;
1576
1577	*f = q_data->format;
1578
1579	if (V4L2_TYPE_IS_CAPTURE(f->type)) {
1580		struct vpe_q_data *s_q_data;
1581		struct v4l2_pix_format_mplane *spix;
1582
1583		/* get colorimetry from the source queue */
1584		s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
1585		spix = &s_q_data->format.fmt.pix_mp;
1586
1587		pix->colorspace = spix->colorspace;
1588		pix->xfer_func = spix->xfer_func;
1589		pix->ycbcr_enc = spix->ycbcr_enc;
1590		pix->quantization = spix->quantization;
1591	}
1592
1593	return 0;
1594}
1595
1596static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
1597		       struct vpe_fmt *fmt, int type)
1598{
1599	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
1600	struct v4l2_plane_pix_format *plane_fmt;
1601	unsigned int w_align;
1602	int i, depth, depth_bytes, height;
1603	unsigned int stride = 0;
1604	const struct v4l2_format_info *finfo;
1605
1606	if (!fmt || !(fmt->types & type)) {
1607		vpe_dbg(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
1608			pix->pixelformat);
1609		fmt = __find_format(V4L2_PIX_FMT_YUYV);
1610	}
1611
1612	if (pix->field != V4L2_FIELD_NONE &&
1613	    pix->field != V4L2_FIELD_ALTERNATE &&
1614	    pix->field != V4L2_FIELD_SEQ_TB &&
1615	    pix->field != V4L2_FIELD_SEQ_BT)
1616		pix->field = V4L2_FIELD_NONE;
1617
1618	depth = fmt->vpdma_fmt[VPE_LUMA]->depth;
1619
1620	/*
1621	 * the line stride should 16 byte aligned for VPDMA to work, based on
1622	 * the bytes per pixel, figure out how much the width should be aligned
1623	 * to make sure line stride is 16 byte aligned
1624	 */
1625	depth_bytes = depth >> 3;
1626
1627	if (depth_bytes == 3) {
1628		/*
1629		 * if bpp is 3(as in some RGB formats), the pixel width doesn't
1630		 * really help in ensuring line stride is 16 byte aligned
1631		 */
1632		w_align = 4;
1633	} else {
1634		/*
1635		 * for the remainder bpp(4, 2 and 1), the pixel width alignment
1636		 * can ensure a line stride alignment of 16 bytes. For example,
1637		 * if bpp is 2, then the line stride can be 16 byte aligned if
1638		 * the width is 8 byte aligned
1639		 */
1640
1641		/*
1642		 * HACK: using order_base_2() here causes lots of asm output
1643		 * errors with smatch, on i386:
1644		 * ./arch/x86/include/asm/bitops.h:457:22:
1645		 *		 warning: asm output is not an lvalue
1646		 * Perhaps some gcc optimization is doing the wrong thing
1647		 * there.
1648		 * Let's get rid of them by doing the calculus on two steps
1649		 */
1650		w_align = roundup_pow_of_two(VPDMA_DESC_ALIGN / depth_bytes);
1651		w_align = ilog2(w_align);
1652	}
1653
1654	v4l_bound_align_image(&pix->width, MIN_W, MAX_W, w_align,
1655			      &pix->height, MIN_H, MAX_H, H_ALIGN,
1656			      S_ALIGN);
1657
1658	if (!pix->num_planes || pix->num_planes > 2)
1659		pix->num_planes = fmt->coplanar ? 2 : 1;
1660	else if (pix->num_planes > 1 && !fmt->coplanar)
1661		pix->num_planes = 1;
1662
1663	pix->pixelformat = fmt->fourcc;
1664	finfo = v4l2_format_info(fmt->fourcc);
1665
1666	/*
1667	 * For the actual image parameters, we need to consider the field
1668	 * height of the image for SEQ_XX buffers.
1669	 */
1670	if (pix->field == V4L2_FIELD_SEQ_TB || pix->field == V4L2_FIELD_SEQ_BT)
1671		height = pix->height / 2;
1672	else
1673		height = pix->height;
1674
1675	if (!pix->colorspace) {
1676		if (v4l2_is_format_rgb(finfo)) {
1677			pix->colorspace = V4L2_COLORSPACE_SRGB;
1678		} else {
1679			if (height > 1280)	/* HD */
1680				pix->colorspace = V4L2_COLORSPACE_REC709;
1681			else			/* SD */
1682				pix->colorspace = V4L2_COLORSPACE_SMPTE170M;
1683		}
1684	}
1685
1686	memset(pix->reserved, 0, sizeof(pix->reserved));
1687	for (i = 0; i < pix->num_planes; i++) {
1688		plane_fmt = &pix->plane_fmt[i];
1689		depth = fmt->vpdma_fmt[i]->depth;
1690
1691		stride = (pix->width * fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
1692		if (stride > plane_fmt->bytesperline)
1693			plane_fmt->bytesperline = stride;
1694
1695		plane_fmt->bytesperline = clamp_t(u32, plane_fmt->bytesperline,
1696						  stride,
1697						  VPDMA_MAX_STRIDE);
1698
1699		plane_fmt->bytesperline = ALIGN(plane_fmt->bytesperline,
1700						VPDMA_STRIDE_ALIGN);
1701
1702		if (i == VPE_LUMA) {
1703			plane_fmt->sizeimage = pix->height *
1704					       plane_fmt->bytesperline;
1705
1706			if (pix->num_planes == 1 && fmt->coplanar)
1707				plane_fmt->sizeimage += pix->height *
1708					plane_fmt->bytesperline *
1709					fmt->vpdma_fmt[VPE_CHROMA]->depth >> 3;
1710
1711		} else { /* i == VIP_CHROMA */
1712			plane_fmt->sizeimage = (pix->height *
1713					       plane_fmt->bytesperline *
1714					       depth) >> 3;
1715		}
1716		memset(plane_fmt->reserved, 0, sizeof(plane_fmt->reserved));
1717	}
1718
1719	return 0;
1720}
1721
1722static int vpe_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
1723{
1724	struct vpe_ctx *ctx = file->private_data;
1725	struct vpe_fmt *fmt = find_format(f);
1726
1727	if (V4L2_TYPE_IS_OUTPUT(f->type))
1728		return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_OUTPUT);
1729	else
1730		return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_CAPTURE);
1731}
1732
1733static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f)
1734{
1735	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
1736	struct v4l2_pix_format_mplane *qpix;
1737	struct vpe_q_data *q_data;
1738	struct vb2_queue *vq;
1739
1740	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
1741	if (!vq)
1742		return -EINVAL;
1743
1744	if (vb2_is_busy(vq)) {
1745		vpe_err(ctx->dev, "queue busy\n");
1746		return -EBUSY;
1747	}
1748
1749	q_data = get_q_data(ctx, f->type);
1750	if (!q_data)
1751		return -EINVAL;
1752
1753	qpix = &q_data->format.fmt.pix_mp;
1754	q_data->fmt		= find_format(f);
1755	q_data->format = *f;
1756
1757	q_data->c_rect.left	= 0;
1758	q_data->c_rect.top	= 0;
1759	q_data->c_rect.width	= pix->width;
1760	q_data->c_rect.height	= pix->height;
1761
1762	if (qpix->field == V4L2_FIELD_ALTERNATE)
1763		q_data->flags |= Q_DATA_INTERLACED_ALTERNATE;
1764	else if (qpix->field == V4L2_FIELD_SEQ_TB)
1765		q_data->flags |= Q_DATA_INTERLACED_SEQ_TB;
1766	else if (qpix->field == V4L2_FIELD_SEQ_BT)
1767		q_data->flags |= Q_DATA_INTERLACED_SEQ_BT;
1768	else
1769		q_data->flags &= ~Q_IS_INTERLACED;
1770
1771	/* the crop height is halved for the case of SEQ_XX buffers */
1772	if (q_data->flags & Q_IS_SEQ_XX)
1773		q_data->c_rect.height /= 2;
1774
1775	vpe_dbg(ctx->dev, "Setting format for type %d, wxh: %dx%d, fmt: %d bpl_y %d",
1776		f->type, pix->width, pix->height, pix->pixelformat,
1777		pix->plane_fmt[0].bytesperline);
1778	if (pix->num_planes == 2)
1779		vpe_dbg(ctx->dev, " bpl_uv %d\n",
1780			pix->plane_fmt[1].bytesperline);
1781
1782	return 0;
1783}
1784
1785static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
1786{
1787	int ret;
1788	struct vpe_ctx *ctx = file->private_data;
1789
1790	ret = vpe_try_fmt(file, priv, f);
1791	if (ret)
1792		return ret;
1793
1794	ret = __vpe_s_fmt(ctx, f);
1795	if (ret)
1796		return ret;
1797
1798	if (V4L2_TYPE_IS_OUTPUT(f->type))
1799		set_src_registers(ctx);
1800	else
1801		set_dst_registers(ctx);
1802
1803	return set_srcdst_params(ctx);
1804}
1805
1806static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
1807{
1808	struct vpe_q_data *q_data;
1809	struct v4l2_pix_format_mplane *pix;
1810	int height;
1811
1812	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
1813	    (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT))
1814		return -EINVAL;
1815
1816	q_data = get_q_data(ctx, s->type);
1817	if (!q_data)
1818		return -EINVAL;
1819
1820	pix = &q_data->format.fmt.pix_mp;
1821
1822	switch (s->target) {
1823	case V4L2_SEL_TGT_COMPOSE:
1824		/*
1825		 * COMPOSE target is only valid for capture buffer type, return
1826		 * error for output buffer type
1827		 */
1828		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
1829			return -EINVAL;
1830		break;
1831	case V4L2_SEL_TGT_CROP:
1832		/*
1833		 * CROP target is only valid for output buffer type, return
1834		 * error for capture buffer type
1835		 */
1836		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
1837			return -EINVAL;
1838		break;
1839	/*
1840	 * bound and default crop/compose targets are invalid targets to
1841	 * try/set
1842	 */
1843	default:
1844		return -EINVAL;
1845	}
1846
1847	/*
1848	 * For SEQ_XX buffers, crop height should be less than the height of
1849	 * the field height, not the buffer height
1850	 */
1851	if (q_data->flags & Q_IS_SEQ_XX)
1852		height = pix->height / 2;
1853	else
1854		height = pix->height;
1855
1856	if (s->r.top < 0 || s->r.left < 0) {
1857		vpe_err(ctx->dev, "negative values for top and left\n");
1858		s->r.top = s->r.left = 0;
1859	}
1860
1861	v4l_bound_align_image(&s->r.width, MIN_W, pix->width, 1,
1862		&s->r.height, MIN_H, height, H_ALIGN, S_ALIGN);
1863
1864	/* adjust left/top if cropping rectangle is out of bounds */
1865	if (s->r.left + s->r.width > pix->width)
1866		s->r.left = pix->width - s->r.width;
1867	if (s->r.top + s->r.height > pix->height)
1868		s->r.top = pix->height - s->r.height;
1869
1870	return 0;
1871}
1872
1873static int vpe_g_selection(struct file *file, void *fh,
1874		struct v4l2_selection *s)
1875{
1876	struct vpe_ctx *ctx = file->private_data;
1877	struct vpe_q_data *q_data;
1878	struct v4l2_pix_format_mplane *pix;
1879	bool use_c_rect = false;
1880
1881	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
1882	    (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT))
1883		return -EINVAL;
1884
1885	q_data = get_q_data(ctx, s->type);
1886	if (!q_data)
1887		return -EINVAL;
1888
1889	pix = &q_data->format.fmt.pix_mp;
1890
1891	switch (s->target) {
1892	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
1893	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
1894		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
1895			return -EINVAL;
1896		break;
1897	case V4L2_SEL_TGT_CROP_BOUNDS:
1898	case V4L2_SEL_TGT_CROP_DEFAULT:
1899		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
1900			return -EINVAL;
1901		break;
1902	case V4L2_SEL_TGT_COMPOSE:
1903		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
1904			return -EINVAL;
1905		use_c_rect = true;
1906		break;
1907	case V4L2_SEL_TGT_CROP:
1908		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
1909			return -EINVAL;
1910		use_c_rect = true;
1911		break;
1912	default:
1913		return -EINVAL;
1914	}
1915
1916	if (use_c_rect) {
1917		/*
1918		 * for CROP/COMPOSE target type, return c_rect params from the
1919		 * respective buffer type
1920		 */
1921		s->r = q_data->c_rect;
1922	} else {
1923		/*
1924		 * for DEFAULT/BOUNDS target type, return width and height from
1925		 * S_FMT of the respective buffer type
1926		 */
1927		s->r.left = 0;
1928		s->r.top = 0;
1929		s->r.width = pix->width;
1930		s->r.height = pix->height;
1931	}
1932
1933	return 0;
1934}
1935
1936
1937static int vpe_s_selection(struct file *file, void *fh,
1938		struct v4l2_selection *s)
1939{
1940	struct vpe_ctx *ctx = file->private_data;
1941	struct vpe_q_data *q_data;
1942	struct v4l2_selection sel = *s;
1943	int ret;
1944
1945	ret = __vpe_try_selection(ctx, &sel);
1946	if (ret)
1947		return ret;
1948
1949	q_data = get_q_data(ctx, sel.type);
1950	if (!q_data)
1951		return -EINVAL;
1952
1953	if ((q_data->c_rect.left == sel.r.left) &&
1954			(q_data->c_rect.top == sel.r.top) &&
1955			(q_data->c_rect.width == sel.r.width) &&
1956			(q_data->c_rect.height == sel.r.height)) {
1957		vpe_dbg(ctx->dev,
1958			"requested crop/compose values are already set\n");
1959		return 0;
1960	}
1961
1962	q_data->c_rect = sel.r;
1963
1964	return set_srcdst_params(ctx);
1965}
1966
1967/*
1968 * defines number of buffers/frames a context can process with VPE before
1969 * switching to a different context. default value is 1 buffer per context
1970 */
1971#define V4L2_CID_VPE_BUFS_PER_JOB		(V4L2_CID_USER_TI_VPE_BASE + 0)
1972
1973static int vpe_s_ctrl(struct v4l2_ctrl *ctrl)
1974{
1975	struct vpe_ctx *ctx =
1976		container_of(ctrl->handler, struct vpe_ctx, hdl);
1977
1978	switch (ctrl->id) {
1979	case V4L2_CID_VPE_BUFS_PER_JOB:
1980		ctx->bufs_per_job = ctrl->val;
1981		break;
1982
1983	default:
1984		vpe_err(ctx->dev, "Invalid control\n");
1985		return -EINVAL;
1986	}
1987
1988	return 0;
1989}
1990
1991static const struct v4l2_ctrl_ops vpe_ctrl_ops = {
1992	.s_ctrl = vpe_s_ctrl,
1993};
1994
1995static const struct v4l2_ioctl_ops vpe_ioctl_ops = {
1996	.vidioc_querycap		= vpe_querycap,
1997
1998	.vidioc_enum_fmt_vid_cap	= vpe_enum_fmt,
1999	.vidioc_g_fmt_vid_cap_mplane	= vpe_g_fmt,
2000	.vidioc_try_fmt_vid_cap_mplane	= vpe_try_fmt,
2001	.vidioc_s_fmt_vid_cap_mplane	= vpe_s_fmt,
2002
2003	.vidioc_enum_fmt_vid_out	= vpe_enum_fmt,
2004	.vidioc_g_fmt_vid_out_mplane	= vpe_g_fmt,
2005	.vidioc_try_fmt_vid_out_mplane	= vpe_try_fmt,
2006	.vidioc_s_fmt_vid_out_mplane	= vpe_s_fmt,
2007
2008	.vidioc_g_selection		= vpe_g_selection,
2009	.vidioc_s_selection		= vpe_s_selection,
2010
2011	.vidioc_reqbufs			= v4l2_m2m_ioctl_reqbufs,
2012	.vidioc_querybuf		= v4l2_m2m_ioctl_querybuf,
2013	.vidioc_qbuf			= v4l2_m2m_ioctl_qbuf,
2014	.vidioc_dqbuf			= v4l2_m2m_ioctl_dqbuf,
2015	.vidioc_expbuf			= v4l2_m2m_ioctl_expbuf,
2016	.vidioc_streamon		= v4l2_m2m_ioctl_streamon,
2017	.vidioc_streamoff		= v4l2_m2m_ioctl_streamoff,
2018
2019	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
2020	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
2021};
2022
2023/*
2024 * Queue operations
2025 */
2026static int vpe_queue_setup(struct vb2_queue *vq,
2027			   unsigned int *nbuffers, unsigned int *nplanes,
2028			   unsigned int sizes[], struct device *alloc_devs[])
2029{
2030	int i;
2031	struct vpe_ctx *ctx = vb2_get_drv_priv(vq);
2032	struct vpe_q_data *q_data;
2033	struct v4l2_pix_format_mplane *pix;
2034
2035	q_data = get_q_data(ctx, vq->type);
2036	if (!q_data)
2037		return -EINVAL;
2038
2039	pix = &q_data->format.fmt.pix_mp;
2040	*nplanes = pix->num_planes;
2041
2042	for (i = 0; i < *nplanes; i++)
2043		sizes[i] = pix->plane_fmt[i].sizeimage;
2044
2045	vpe_dbg(ctx->dev, "get %d buffer(s) of size %d", *nbuffers,
2046		sizes[VPE_LUMA]);
2047	if (*nplanes == 2)
2048		vpe_dbg(ctx->dev, " and %d\n", sizes[VPE_CHROMA]);
2049
2050	return 0;
2051}
2052
2053static int vpe_buf_prepare(struct vb2_buffer *vb)
2054{
2055	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
2056	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
2057	struct vpe_q_data *q_data;
2058	struct v4l2_pix_format_mplane *pix;
2059	int i;
2060
2061	vpe_dbg(ctx->dev, "type: %d\n", vb->vb2_queue->type);
2062
2063	q_data = get_q_data(ctx, vb->vb2_queue->type);
2064	if (!q_data)
2065		return -EINVAL;
2066
2067	pix = &q_data->format.fmt.pix_mp;
2068
2069	if (vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
2070		if (!(q_data->flags & Q_IS_INTERLACED)) {
2071			vbuf->field = V4L2_FIELD_NONE;
2072		} else {
2073			if (vbuf->field != V4L2_FIELD_TOP &&
2074			    vbuf->field != V4L2_FIELD_BOTTOM &&
2075			    vbuf->field != V4L2_FIELD_SEQ_TB &&
2076			    vbuf->field != V4L2_FIELD_SEQ_BT)
2077				return -EINVAL;
2078		}
2079	}
2080
2081	for (i = 0; i < pix->num_planes; i++) {
2082		if (vb2_plane_size(vb, i) < pix->plane_fmt[i].sizeimage) {
2083			vpe_err(ctx->dev,
2084				"data will not fit into plane (%lu < %lu)\n",
2085				vb2_plane_size(vb, i),
2086				(long)pix->plane_fmt[i].sizeimage);
2087			return -EINVAL;
2088		}
2089	}
2090
2091	for (i = 0; i < pix->num_planes; i++)
2092		vb2_set_plane_payload(vb, i, pix->plane_fmt[i].sizeimage);
2093
2094	return 0;
2095}
2096
2097static void vpe_buf_queue(struct vb2_buffer *vb)
2098{
2099	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
2100	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
2101
2102	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
2103}
2104
2105static int check_srcdst_sizes(struct vpe_ctx *ctx)
2106{
2107	struct vpe_q_data *s_q_data =  &ctx->q_data[Q_DATA_SRC];
2108	struct vpe_q_data *d_q_data =  &ctx->q_data[Q_DATA_DST];
2109	unsigned int src_w = s_q_data->c_rect.width;
2110	unsigned int src_h = s_q_data->c_rect.height;
2111	unsigned int dst_w = d_q_data->c_rect.width;
2112	unsigned int dst_h = d_q_data->c_rect.height;
2113
2114	if (src_w == dst_w && src_h == dst_h)
2115		return 0;
2116
2117	if (src_h <= SC_MAX_PIXEL_HEIGHT &&
2118	    src_w <= SC_MAX_PIXEL_WIDTH &&
2119	    dst_h <= SC_MAX_PIXEL_HEIGHT &&
2120	    dst_w <= SC_MAX_PIXEL_WIDTH)
2121		return 0;
2122
2123	return -1;
2124}
2125
2126static void vpe_return_all_buffers(struct vpe_ctx *ctx,  struct vb2_queue *q,
2127				   enum vb2_buffer_state state)
2128{
2129	struct vb2_v4l2_buffer *vb;
2130	unsigned long flags;
2131
2132	for (;;) {
2133		if (V4L2_TYPE_IS_OUTPUT(q->type))
2134			vb = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
2135		else
2136			vb = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
2137		if (!vb)
2138			break;
2139		spin_lock_irqsave(&ctx->dev->lock, flags);
2140		v4l2_m2m_buf_done(vb, state);
2141		spin_unlock_irqrestore(&ctx->dev->lock, flags);
2142	}
2143
2144	/*
2145	 * Cleanup the in-transit vb2 buffers that have been
2146	 * removed from their respective queue already but for
2147	 * which procecessing has not been completed yet.
2148	 */
2149	if (V4L2_TYPE_IS_OUTPUT(q->type)) {
2150		spin_lock_irqsave(&ctx->dev->lock, flags);
2151
2152		if (ctx->src_vbs[2])
2153			v4l2_m2m_buf_done(ctx->src_vbs[2], state);
2154
2155		if (ctx->src_vbs[1] && (ctx->src_vbs[1] != ctx->src_vbs[2]))
2156			v4l2_m2m_buf_done(ctx->src_vbs[1], state);
2157
2158		if (ctx->src_vbs[0] &&
2159		    (ctx->src_vbs[0] != ctx->src_vbs[1]) &&
2160		    (ctx->src_vbs[0] != ctx->src_vbs[2]))
2161			v4l2_m2m_buf_done(ctx->src_vbs[0], state);
2162
2163		ctx->src_vbs[2] = NULL;
2164		ctx->src_vbs[1] = NULL;
2165		ctx->src_vbs[0] = NULL;
2166
2167		spin_unlock_irqrestore(&ctx->dev->lock, flags);
2168	} else {
2169		if (ctx->dst_vb) {
2170			spin_lock_irqsave(&ctx->dev->lock, flags);
2171
2172			v4l2_m2m_buf_done(ctx->dst_vb, state);
2173			ctx->dst_vb = NULL;
2174			spin_unlock_irqrestore(&ctx->dev->lock, flags);
2175		}
2176	}
2177}
2178
2179static int vpe_start_streaming(struct vb2_queue *q, unsigned int count)
2180{
2181	struct vpe_ctx *ctx = vb2_get_drv_priv(q);
2182
2183	/* Check any of the size exceed maximum scaling sizes */
2184	if (check_srcdst_sizes(ctx)) {
2185		vpe_err(ctx->dev,
2186			"Conversion setup failed, check source and destination parameters\n"
2187			);
2188		vpe_return_all_buffers(ctx, q, VB2_BUF_STATE_QUEUED);
2189		return -EINVAL;
2190	}
2191
2192	if (ctx->deinterlacing)
2193		config_edi_input_mode(ctx, 0x0);
2194
2195	if (ctx->sequence != 0)
2196		set_srcdst_params(ctx);
2197
2198	return 0;
2199}
2200
2201static void vpe_stop_streaming(struct vb2_queue *q)
2202{
2203	struct vpe_ctx *ctx = vb2_get_drv_priv(q);
2204
2205	vpe_dump_regs(ctx->dev);
2206	vpdma_dump_regs(ctx->dev->vpdma);
2207
2208	vpe_return_all_buffers(ctx, q, VB2_BUF_STATE_ERROR);
2209}
2210
2211static const struct vb2_ops vpe_qops = {
2212	.queue_setup	 = vpe_queue_setup,
2213	.buf_prepare	 = vpe_buf_prepare,
2214	.buf_queue	 = vpe_buf_queue,
2215	.wait_prepare	 = vb2_ops_wait_prepare,
2216	.wait_finish	 = vb2_ops_wait_finish,
2217	.start_streaming = vpe_start_streaming,
2218	.stop_streaming  = vpe_stop_streaming,
2219};
2220
2221static int queue_init(void *priv, struct vb2_queue *src_vq,
2222		      struct vb2_queue *dst_vq)
2223{
2224	struct vpe_ctx *ctx = priv;
2225	struct vpe_dev *dev = ctx->dev;
2226	int ret;
2227
2228	memset(src_vq, 0, sizeof(*src_vq));
2229	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
2230	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
2231	src_vq->drv_priv = ctx;
2232	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
2233	src_vq->ops = &vpe_qops;
2234	src_vq->mem_ops = &vb2_dma_contig_memops;
2235	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
2236	src_vq->lock = &dev->dev_mutex;
2237	src_vq->dev = dev->v4l2_dev.dev;
2238
2239	ret = vb2_queue_init(src_vq);
2240	if (ret)
2241		return ret;
2242
2243	memset(dst_vq, 0, sizeof(*dst_vq));
2244	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
2245	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
2246	dst_vq->drv_priv = ctx;
2247	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
2248	dst_vq->ops = &vpe_qops;
2249	dst_vq->mem_ops = &vb2_dma_contig_memops;
2250	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
2251	dst_vq->lock = &dev->dev_mutex;
2252	dst_vq->dev = dev->v4l2_dev.dev;
2253
2254	return vb2_queue_init(dst_vq);
2255}
2256
2257static const struct v4l2_ctrl_config vpe_bufs_per_job = {
2258	.ops = &vpe_ctrl_ops,
2259	.id = V4L2_CID_VPE_BUFS_PER_JOB,
2260	.name = "Buffers Per Transaction",
2261	.type = V4L2_CTRL_TYPE_INTEGER,
2262	.def = VPE_DEF_BUFS_PER_JOB,
2263	.min = 1,
2264	.max = VIDEO_MAX_FRAME,
2265	.step = 1,
2266};
2267
2268/*
2269 * File operations
2270 */
2271static int vpe_open(struct file *file)
2272{
2273	struct vpe_dev *dev = video_drvdata(file);
2274	struct vpe_q_data *s_q_data;
2275	struct v4l2_ctrl_handler *hdl;
2276	struct vpe_ctx *ctx;
2277	struct v4l2_pix_format_mplane *pix;
2278	int ret;
2279
2280	vpe_dbg(dev, "vpe_open\n");
2281
2282	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
2283	if (!ctx)
2284		return -ENOMEM;
2285
2286	ctx->dev = dev;
2287
2288	if (mutex_lock_interruptible(&dev->dev_mutex)) {
2289		ret = -ERESTARTSYS;
2290		goto free_ctx;
2291	}
2292
2293	ret = vpdma_create_desc_list(&ctx->desc_list, VPE_DESC_LIST_SIZE,
2294			VPDMA_LIST_TYPE_NORMAL);
2295	if (ret != 0)
2296		goto unlock;
2297
2298	ret = vpdma_alloc_desc_buf(&ctx->mmr_adb, sizeof(struct vpe_mmr_adb));
2299	if (ret != 0)
2300		goto free_desc_list;
2301
2302	ret = vpdma_alloc_desc_buf(&ctx->sc_coeff_h, SC_COEF_SRAM_SIZE);
2303	if (ret != 0)
2304		goto free_mmr_adb;
2305
2306	ret = vpdma_alloc_desc_buf(&ctx->sc_coeff_v, SC_COEF_SRAM_SIZE);
2307	if (ret != 0)
2308		goto free_sc_h;
2309
2310	init_adb_hdrs(ctx);
2311
2312	v4l2_fh_init(&ctx->fh, video_devdata(file));
2313	file->private_data = ctx;
2314
2315	hdl = &ctx->hdl;
2316	v4l2_ctrl_handler_init(hdl, 1);
2317	v4l2_ctrl_new_custom(hdl, &vpe_bufs_per_job, NULL);
2318	if (hdl->error) {
2319		ret = hdl->error;
2320		goto exit_fh;
2321	}
2322	ctx->fh.ctrl_handler = hdl;
2323	v4l2_ctrl_handler_setup(hdl);
2324
2325	s_q_data = &ctx->q_data[Q_DATA_SRC];
2326	pix = &s_q_data->format.fmt.pix_mp;
2327	s_q_data->fmt = __find_format(V4L2_PIX_FMT_YUYV);
2328	pix->pixelformat = s_q_data->fmt->fourcc;
2329	s_q_data->format.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
2330	pix->width = 1920;
2331	pix->height = 1080;
2332	pix->num_planes = 1;
2333	pix->plane_fmt[VPE_LUMA].bytesperline = (pix->width *
2334			s_q_data->fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
2335	pix->plane_fmt[VPE_LUMA].sizeimage =
2336			pix->plane_fmt[VPE_LUMA].bytesperline *
2337			pix->height;
2338	pix->colorspace = V4L2_COLORSPACE_REC709;
2339	pix->xfer_func = V4L2_XFER_FUNC_DEFAULT;
2340	pix->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT;
2341	pix->quantization = V4L2_QUANTIZATION_DEFAULT;
2342	pix->field = V4L2_FIELD_NONE;
2343	s_q_data->c_rect.left = 0;
2344	s_q_data->c_rect.top = 0;
2345	s_q_data->c_rect.width = pix->width;
2346	s_q_data->c_rect.height = pix->height;
2347	s_q_data->flags = 0;
2348
2349	ctx->q_data[Q_DATA_DST] = *s_q_data;
2350	ctx->q_data[Q_DATA_DST].format.type =
2351			V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
2352
2353	set_dei_shadow_registers(ctx);
2354	set_src_registers(ctx);
2355	set_dst_registers(ctx);
2356	ret = set_srcdst_params(ctx);
2357	if (ret)
2358		goto exit_fh;
2359
2360	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx, &queue_init);
2361
2362	if (IS_ERR(ctx->fh.m2m_ctx)) {
2363		ret = PTR_ERR(ctx->fh.m2m_ctx);
2364		goto exit_fh;
2365	}
2366
2367	v4l2_fh_add(&ctx->fh);
2368
2369	/*
2370	 * for now, just report the creation of the first instance, we can later
2371	 * optimize the driver to enable or disable clocks when the first
2372	 * instance is created or the last instance released
2373	 */
2374	if (atomic_inc_return(&dev->num_instances) == 1)
2375		vpe_dbg(dev, "first instance created\n");
2376
2377	ctx->bufs_per_job = VPE_DEF_BUFS_PER_JOB;
2378
2379	ctx->load_mmrs = true;
2380
2381	vpe_dbg(dev, "created instance %p, m2m_ctx: %p\n",
2382		ctx, ctx->fh.m2m_ctx);
2383
2384	mutex_unlock(&dev->dev_mutex);
2385
2386	return 0;
2387exit_fh:
2388	v4l2_ctrl_handler_free(hdl);
2389	v4l2_fh_exit(&ctx->fh);
2390	vpdma_free_desc_buf(&ctx->sc_coeff_v);
2391free_sc_h:
2392	vpdma_free_desc_buf(&ctx->sc_coeff_h);
2393free_mmr_adb:
2394	vpdma_free_desc_buf(&ctx->mmr_adb);
2395free_desc_list:
2396	vpdma_free_desc_list(&ctx->desc_list);
2397unlock:
2398	mutex_unlock(&dev->dev_mutex);
2399free_ctx:
2400	kfree(ctx);
2401	return ret;
2402}
2403
2404static int vpe_release(struct file *file)
2405{
2406	struct vpe_dev *dev = video_drvdata(file);
2407	struct vpe_ctx *ctx = file->private_data;
2408
2409	vpe_dbg(dev, "releasing instance %p\n", ctx);
2410
2411	mutex_lock(&dev->dev_mutex);
2412	free_mv_buffers(ctx);
2413
2414	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
2415	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
2416	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_h);
2417	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_v);
2418
2419	vpdma_free_desc_list(&ctx->desc_list);
2420	vpdma_free_desc_buf(&ctx->mmr_adb);
2421
2422	vpdma_free_desc_buf(&ctx->sc_coeff_v);
2423	vpdma_free_desc_buf(&ctx->sc_coeff_h);
2424
2425	v4l2_fh_del(&ctx->fh);
2426	v4l2_fh_exit(&ctx->fh);
2427	v4l2_ctrl_handler_free(&ctx->hdl);
2428	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
2429
2430	kfree(ctx);
2431
2432	/*
2433	 * for now, just report the release of the last instance, we can later
2434	 * optimize the driver to enable or disable clocks when the first
2435	 * instance is created or the last instance released
2436	 */
2437	if (atomic_dec_return(&dev->num_instances) == 0)
2438		vpe_dbg(dev, "last instance released\n");
2439
2440	mutex_unlock(&dev->dev_mutex);
2441
2442	return 0;
2443}
2444
2445static const struct v4l2_file_operations vpe_fops = {
2446	.owner		= THIS_MODULE,
2447	.open		= vpe_open,
2448	.release	= vpe_release,
2449	.poll		= v4l2_m2m_fop_poll,
2450	.unlocked_ioctl	= video_ioctl2,
2451	.mmap		= v4l2_m2m_fop_mmap,
2452};
2453
2454static const struct video_device vpe_videodev = {
2455	.name		= VPE_MODULE_NAME,
2456	.fops		= &vpe_fops,
2457	.ioctl_ops	= &vpe_ioctl_ops,
2458	.minor		= -1,
2459	.release	= video_device_release_empty,
2460	.vfl_dir	= VFL_DIR_M2M,
2461	.device_caps	= V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_STREAMING,
2462};
2463
2464static const struct v4l2_m2m_ops m2m_ops = {
2465	.device_run	= device_run,
2466	.job_ready	= job_ready,
2467	.job_abort	= job_abort,
2468};
2469
2470static int vpe_runtime_get(struct platform_device *pdev)
2471{
2472	int r;
2473
2474	dev_dbg(&pdev->dev, "vpe_runtime_get\n");
2475
2476	r = pm_runtime_get_sync(&pdev->dev);
2477	WARN_ON(r < 0);
2478	if (r)
2479		pm_runtime_put_noidle(&pdev->dev);
2480	return r < 0 ? r : 0;
2481}
2482
2483static void vpe_runtime_put(struct platform_device *pdev)
2484{
2485
2486	int r;
2487
2488	dev_dbg(&pdev->dev, "vpe_runtime_put\n");
2489
2490	r = pm_runtime_put_sync(&pdev->dev);
2491	WARN_ON(r < 0 && r != -ENOSYS);
2492}
2493
2494static void vpe_fw_cb(struct platform_device *pdev)
2495{
2496	struct vpe_dev *dev = platform_get_drvdata(pdev);
2497	struct video_device *vfd;
2498	int ret;
2499
2500	vfd = &dev->vfd;
2501	*vfd = vpe_videodev;
2502	vfd->lock = &dev->dev_mutex;
2503	vfd->v4l2_dev = &dev->v4l2_dev;
2504
2505	ret = video_register_device(vfd, VFL_TYPE_VIDEO, 0);
2506	if (ret) {
2507		vpe_err(dev, "Failed to register video device\n");
2508
2509		vpe_set_clock_enable(dev, 0);
2510		vpe_runtime_put(pdev);
2511		pm_runtime_disable(&pdev->dev);
2512		v4l2_m2m_release(dev->m2m_dev);
2513		v4l2_device_unregister(&dev->v4l2_dev);
2514
2515		return;
2516	}
2517
2518	video_set_drvdata(vfd, dev);
2519	dev_info(dev->v4l2_dev.dev, "Device registered as /dev/video%d\n",
2520		vfd->num);
2521}
2522
2523static int vpe_probe(struct platform_device *pdev)
2524{
2525	struct vpe_dev *dev;
2526	int ret, irq, func;
2527
2528	ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
2529	if (ret) {
2530		dev_err(&pdev->dev,
2531			"32-bit consistent DMA enable failed\n");
2532		return ret;
2533	}
2534
2535	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
2536	if (!dev)
2537		return -ENOMEM;
2538
2539	spin_lock_init(&dev->lock);
2540
2541	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
2542	if (ret)
2543		return ret;
2544
2545	atomic_set(&dev->num_instances, 0);
2546	mutex_init(&dev->dev_mutex);
2547
2548	dev->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
2549						"vpe_top");
2550	if (!dev->res) {
2551		dev_err(&pdev->dev, "missing 'vpe_top' resources data\n");
2552		return -ENODEV;
2553	}
2554
2555	/*
2556	 * HACK: we get resource info from device tree in the form of a list of
2557	 * VPE sub blocks, the driver currently uses only the base of vpe_top
2558	 * for register access, the driver should be changed later to access
2559	 * registers based on the sub block base addresses
2560	 */
2561	dev->base = devm_ioremap(&pdev->dev, dev->res->start, SZ_32K);
2562	if (!dev->base) {
2563		ret = -ENOMEM;
2564		goto v4l2_dev_unreg;
2565	}
2566
2567	irq = platform_get_irq(pdev, 0);
2568	ret = devm_request_irq(&pdev->dev, irq, vpe_irq, 0, VPE_MODULE_NAME,
2569			dev);
2570	if (ret)
2571		goto v4l2_dev_unreg;
2572
2573	platform_set_drvdata(pdev, dev);
2574
2575	dev->m2m_dev = v4l2_m2m_init(&m2m_ops);
2576	if (IS_ERR(dev->m2m_dev)) {
2577		vpe_err(dev, "Failed to init mem2mem device\n");
2578		ret = PTR_ERR(dev->m2m_dev);
2579		goto v4l2_dev_unreg;
2580	}
2581
2582	pm_runtime_enable(&pdev->dev);
2583
2584	ret = vpe_runtime_get(pdev);
2585	if (ret)
2586		goto rel_m2m;
2587
2588	/* Perform clk enable followed by reset */
2589	vpe_set_clock_enable(dev, 1);
2590
2591	vpe_top_reset(dev);
2592
2593	func = read_field_reg(dev, VPE_PID, VPE_PID_FUNC_MASK,
2594		VPE_PID_FUNC_SHIFT);
2595	vpe_dbg(dev, "VPE PID function %x\n", func);
2596
2597	vpe_top_vpdma_reset(dev);
2598
2599	dev->sc = sc_create(pdev, "sc");
2600	if (IS_ERR(dev->sc)) {
2601		ret = PTR_ERR(dev->sc);
2602		goto runtime_put;
2603	}
2604
2605	dev->csc = csc_create(pdev, "csc");
2606	if (IS_ERR(dev->csc)) {
2607		ret = PTR_ERR(dev->csc);
2608		goto runtime_put;
2609	}
2610
2611	dev->vpdma = &dev->vpdma_data;
2612	ret = vpdma_create(pdev, dev->vpdma, vpe_fw_cb);
2613	if (ret)
2614		goto runtime_put;
2615
2616	return 0;
2617
2618runtime_put:
2619	vpe_runtime_put(pdev);
2620rel_m2m:
2621	pm_runtime_disable(&pdev->dev);
2622	v4l2_m2m_release(dev->m2m_dev);
2623v4l2_dev_unreg:
2624	v4l2_device_unregister(&dev->v4l2_dev);
2625
2626	return ret;
2627}
2628
2629static int vpe_remove(struct platform_device *pdev)
2630{
2631	struct vpe_dev *dev = platform_get_drvdata(pdev);
2632
2633	v4l2_info(&dev->v4l2_dev, "Removing " VPE_MODULE_NAME);
2634
2635	v4l2_m2m_release(dev->m2m_dev);
2636	video_unregister_device(&dev->vfd);
2637	v4l2_device_unregister(&dev->v4l2_dev);
2638
2639	vpe_set_clock_enable(dev, 0);
2640	vpe_runtime_put(pdev);
2641	pm_runtime_disable(&pdev->dev);
2642
2643	return 0;
2644}
2645
2646#if defined(CONFIG_OF)
2647static const struct of_device_id vpe_of_match[] = {
2648	{
2649		.compatible = "ti,dra7-vpe",
2650	},
2651	{},
2652};
2653MODULE_DEVICE_TABLE(of, vpe_of_match);
2654#endif
2655
2656static struct platform_driver vpe_pdrv = {
2657	.probe		= vpe_probe,
2658	.remove		= vpe_remove,
2659	.driver		= {
2660		.name	= VPE_MODULE_NAME,
2661		.of_match_table = of_match_ptr(vpe_of_match),
2662	},
2663};
2664
2665module_platform_driver(vpe_pdrv);
2666
2667MODULE_DESCRIPTION("TI VPE driver");
2668MODULE_AUTHOR("Dale Farnsworth, <dale@farnsworth.org>");
2669MODULE_LICENSE("GPL");
2670