coda-bit.c 54.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
/*
 * Coda multi-standard codec IP - BIT processor functions
 *
 * Copyright (C) 2012 Vista Silicon S.L.
 *    Javier Martin, <javier.martin@vista-silicon.com>
 *    Xavier Duret
 * Copyright (C) 2012-2014 Philipp Zabel, Pengutronix
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 */

#include <linux/clk.h>
#include <linux/irqreturn.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/reset.h>
20
#include <linux/slab.h>
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
#include <linux/videodev2.h>

#include <media/v4l2-common.h>
#include <media/v4l2-ctrls.h>
#include <media/v4l2-fh.h>
#include <media/v4l2-mem2mem.h>
#include <media/videobuf2-core.h>
#include <media/videobuf2-dma-contig.h>
#include <media/videobuf2-vmalloc.h>

#include "coda.h"

#define CODA7_PS_BUF_SIZE	0x28000
#define CODA9_PS_SAVE_SIZE	(512 * 1024)

#define CODA_DEFAULT_GAMMA	4096
#define CODA9_DEFAULT_GAMMA	24576	/* 0.75 * 32768 */

static inline int coda_is_initialized(struct coda_dev *dev)
{
P
Philipp Zabel 已提交
41
	return coda_read(dev, CODA_REG_BIT_CUR_PC) != 0;
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
}

static inline unsigned long coda_isbusy(struct coda_dev *dev)
{
	return coda_read(dev, CODA_REG_BIT_BUSY);
}

static int coda_wait_timeout(struct coda_dev *dev)
{
	unsigned long timeout = jiffies + msecs_to_jiffies(1000);

	while (coda_isbusy(dev)) {
		if (time_after(jiffies, timeout))
			return -ETIMEDOUT;
	}
	return 0;
}

static void coda_command_async(struct coda_ctx *ctx, int cmd)
{
	struct coda_dev *dev = ctx->dev;

	if (dev->devtype->product == CODA_960 ||
	    dev->devtype->product == CODA_7541) {
		/* Restore context related registers to CODA */
		coda_write(dev, ctx->bit_stream_param,
				CODA_REG_BIT_BIT_STREAM_PARAM);
		coda_write(dev, ctx->frm_dis_flg,
				CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
		coda_write(dev, ctx->frame_mem_ctrl,
				CODA_REG_BIT_FRAME_MEM_CTRL);
		coda_write(dev, ctx->workbuf.paddr, CODA_REG_BIT_WORK_BUF_ADDR);
	}

	if (dev->devtype->product == CODA_960) {
		coda_write(dev, 1, CODA9_GDI_WPROT_ERR_CLR);
		coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
	}

	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);

	coda_write(dev, ctx->idx, CODA_REG_BIT_RUN_INDEX);
	coda_write(dev, ctx->params.codec_mode, CODA_REG_BIT_RUN_COD_STD);
	coda_write(dev, ctx->params.codec_mode_aux, CODA7_REG_BIT_RUN_AUX_STD);

	coda_write(dev, cmd, CODA_REG_BIT_RUN_COMMAND);
}

static int coda_command_sync(struct coda_ctx *ctx, int cmd)
{
	struct coda_dev *dev = ctx->dev;

	coda_command_async(ctx, cmd);
	return coda_wait_timeout(dev);
}

int coda_hw_reset(struct coda_ctx *ctx)
{
	struct coda_dev *dev = ctx->dev;
	unsigned long timeout;
	unsigned int idx;
	int ret;

	if (!dev->rstc)
		return -ENOENT;

	idx = coda_read(dev, CODA_REG_BIT_RUN_INDEX);

	if (dev->devtype->product == CODA_960) {
		timeout = jiffies + msecs_to_jiffies(100);
		coda_write(dev, 0x11, CODA9_GDI_BUS_CTRL);
		while (coda_read(dev, CODA9_GDI_BUS_STATUS) != 0x77) {
			if (time_after(jiffies, timeout))
				return -ETIME;
			cpu_relax();
		}
	}

	ret = reset_control_reset(dev->rstc);
	if (ret < 0)
		return ret;

	if (dev->devtype->product == CODA_960)
		coda_write(dev, 0x00, CODA9_GDI_BUS_CTRL);
	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
	coda_write(dev, CODA_REG_RUN_ENABLE, CODA_REG_BIT_CODE_RUN);
	ret = coda_wait_timeout(dev);
	coda_write(dev, idx, CODA_REG_BIT_RUN_INDEX);

	return ret;
}

static void coda_kfifo_sync_from_device(struct coda_ctx *ctx)
{
	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
	struct coda_dev *dev = ctx->dev;
	u32 rd_ptr;

	rd_ptr = coda_read(dev, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
	kfifo->out = (kfifo->in & ~kfifo->mask) |
		      (rd_ptr - ctx->bitstream.paddr);
	if (kfifo->out > kfifo->in)
		kfifo->out -= kfifo->mask + 1;
}

static void coda_kfifo_sync_to_device_full(struct coda_ctx *ctx)
{
	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
	struct coda_dev *dev = ctx->dev;
	u32 rd_ptr, wr_ptr;

	rd_ptr = ctx->bitstream.paddr + (kfifo->out & kfifo->mask);
	coda_write(dev, rd_ptr, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
	wr_ptr = ctx->bitstream.paddr + (kfifo->in & kfifo->mask);
	coda_write(dev, wr_ptr, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
}

static void coda_kfifo_sync_to_device_write(struct coda_ctx *ctx)
{
	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
	struct coda_dev *dev = ctx->dev;
	u32 wr_ptr;

	wr_ptr = ctx->bitstream.paddr + (kfifo->in & kfifo->mask);
	coda_write(dev, wr_ptr, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
}

P
Philipp Zabel 已提交
169 170
static int coda_bitstream_queue(struct coda_ctx *ctx,
				struct vb2_buffer *src_buf)
171 172 173 174
{
	u32 src_size = vb2_get_plane_payload(src_buf, 0);
	u32 n;

P
Philipp Zabel 已提交
175 176
	n = kfifo_in(&ctx->bitstream_fifo, vb2_plane_vaddr(src_buf, 0),
		     src_size);
177 178 179
	if (n < src_size)
		return -ENOSPC;

P
Philipp Zabel 已提交
180 181 182
	dma_sync_single_for_device(&ctx->dev->plat_dev->dev,
				   ctx->bitstream.paddr, ctx->bitstream.size,
				   DMA_TO_DEVICE);
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219

	src_buf->v4l2_buf.sequence = ctx->qsequence++;

	return 0;
}

static bool coda_bitstream_try_queue(struct coda_ctx *ctx,
				     struct vb2_buffer *src_buf)
{
	int ret;

	if (coda_get_bitstream_payload(ctx) +
	    vb2_get_plane_payload(src_buf, 0) + 512 >= ctx->bitstream.size)
		return false;

	if (vb2_plane_vaddr(src_buf, 0) == NULL) {
		v4l2_err(&ctx->dev->v4l2_dev, "trying to queue empty buffer\n");
		return true;
	}

	ret = coda_bitstream_queue(ctx, src_buf);
	if (ret < 0) {
		v4l2_err(&ctx->dev->v4l2_dev, "bitstream buffer overflow\n");
		return false;
	}
	/* Sync read pointer to device */
	if (ctx == v4l2_m2m_get_curr_priv(ctx->dev->m2m_dev))
		coda_kfifo_sync_to_device_write(ctx);

	ctx->hold = false;

	return true;
}

void coda_fill_bitstream(struct coda_ctx *ctx)
{
	struct vb2_buffer *src_buf;
220 221
	struct coda_buffer_meta *meta;
	u32 start;
222 223

	while (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) > 0) {
224 225 226 227 228 229 230 231
		/*
		 * Only queue a single JPEG into the bitstream buffer, except
		 * to increase payload over 512 bytes or if in hold state.
		 */
		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_JPEG &&
		    (coda_get_bitstream_payload(ctx) >= 512) && !ctx->hold)
			break;

232 233
		src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);

234 235 236 237
		/* Buffer start position */
		start = ctx->bitstream_fifo.kfifo.in &
			ctx->bitstream_fifo.kfifo.mask;

238 239 240 241 242 243 244
		if (coda_bitstream_try_queue(ctx, src_buf)) {
			/*
			 * Source buffer is queued in the bitstream ringbuffer;
			 * queue the timestamp and mark source buffer as done
			 */
			src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);

245 246 247 248 249 250 251 252 253 254
			meta = kmalloc(sizeof(*meta), GFP_KERNEL);
			if (meta) {
				meta->sequence = src_buf->v4l2_buf.sequence;
				meta->timecode = src_buf->v4l2_buf.timecode;
				meta->timestamp = src_buf->v4l2_buf.timestamp;
				meta->start = start;
				meta->end = ctx->bitstream_fifo.kfifo.in &
					    ctx->bitstream_fifo.kfifo.mask;
				list_add_tail(&meta->list,
					      &ctx->buffer_meta_list);
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
			}

			v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
		} else {
			break;
		}
	}
}

void coda_bit_stream_end_flag(struct coda_ctx *ctx)
{
	struct coda_dev *dev = ctx->dev;

	ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;

P
Philipp Zabel 已提交
270
	/* If this context is currently running, update the hardware flag */
271 272 273
	if ((dev->devtype->product == CODA_960) &&
	    coda_isbusy(dev) &&
	    (ctx->idx == coda_read(dev, CODA_REG_BIT_RUN_INDEX))) {
P
Philipp Zabel 已提交
274 275
		coda_write(dev, ctx->bit_stream_param,
			   CODA_REG_BIT_BIT_STREAM_PARAM);
276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339
	}
}

static void coda_parabuf_write(struct coda_ctx *ctx, int index, u32 value)
{
	struct coda_dev *dev = ctx->dev;
	u32 *p = ctx->parabuf.vaddr;

	if (dev->devtype->product == CODA_DX6)
		p[index] = value;
	else
		p[index ^ 1] = value;
}

static void coda_free_framebuffers(struct coda_ctx *ctx)
{
	int i;

	for (i = 0; i < CODA_MAX_FRAMEBUFFERS; i++)
		coda_free_aux_buf(ctx->dev, &ctx->internal_frames[i]);
}

static int coda_alloc_framebuffers(struct coda_ctx *ctx,
				   struct coda_q_data *q_data, u32 fourcc)
{
	struct coda_dev *dev = ctx->dev;
	int width, height;
	dma_addr_t paddr;
	int ysize;
	int ret;
	int i;

	if (ctx->codec && (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
	     ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264)) {
		width = round_up(q_data->width, 16);
		height = round_up(q_data->height, 16);
	} else {
		width = round_up(q_data->width, 8);
		height = q_data->height;
	}
	ysize = width * height;

	/* Allocate frame buffers */
	for (i = 0; i < ctx->num_internal_frames; i++) {
		size_t size;
		char *name;

		size = ysize + ysize / 2;
		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 &&
		    dev->devtype->product != CODA_DX6)
			size += ysize / 4;
		name = kasprintf(GFP_KERNEL, "fb%d", i);
		ret = coda_alloc_context_buf(ctx, &ctx->internal_frames[i],
					     size, name);
		kfree(name);
		if (ret < 0) {
			coda_free_framebuffers(ctx);
			return ret;
		}
	}

	/* Register frame buffers in the parameter buffer */
	for (i = 0; i < ctx->num_internal_frames; i++) {
		paddr = ctx->internal_frames[i].paddr;
P
Philipp Zabel 已提交
340 341 342 343
		/* Start addresses of Y, Cb, Cr planes */
		coda_parabuf_write(ctx, i * 3 + 0, paddr);
		coda_parabuf_write(ctx, i * 3 + 1, paddr + ysize);
		coda_parabuf_write(ctx, i * 3 + 2, paddr + ysize + ysize / 4);
344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399

		/* mvcol buffer for h.264 */
		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 &&
		    dev->devtype->product != CODA_DX6)
			coda_parabuf_write(ctx, 96 + i,
					   ctx->internal_frames[i].paddr +
					   ysize + ysize/4 + ysize/4);
	}

	/* mvcol buffer for mpeg4 */
	if ((dev->devtype->product != CODA_DX6) &&
	    (ctx->codec->src_fourcc == V4L2_PIX_FMT_MPEG4))
		coda_parabuf_write(ctx, 97, ctx->internal_frames[i].paddr +
					    ysize + ysize/4 + ysize/4);

	return 0;
}

static void coda_free_context_buffers(struct coda_ctx *ctx)
{
	struct coda_dev *dev = ctx->dev;

	coda_free_aux_buf(dev, &ctx->slicebuf);
	coda_free_aux_buf(dev, &ctx->psbuf);
	if (dev->devtype->product != CODA_DX6)
		coda_free_aux_buf(dev, &ctx->workbuf);
}

static int coda_alloc_context_buffers(struct coda_ctx *ctx,
				      struct coda_q_data *q_data)
{
	struct coda_dev *dev = ctx->dev;
	size_t size;
	int ret;

	if (dev->devtype->product == CODA_DX6)
		return 0;

	if (ctx->psbuf.vaddr) {
		v4l2_err(&dev->v4l2_dev, "psmembuf still allocated\n");
		return -EBUSY;
	}
	if (ctx->slicebuf.vaddr) {
		v4l2_err(&dev->v4l2_dev, "slicebuf still allocated\n");
		return -EBUSY;
	}
	if (ctx->workbuf.vaddr) {
		v4l2_err(&dev->v4l2_dev, "context buffer still allocated\n");
		ret = -EBUSY;
		return -ENOMEM;
	}

	if (q_data->fourcc == V4L2_PIX_FMT_H264) {
		/* worst case slice size */
		size = (DIV_ROUND_UP(q_data->width, 16) *
			DIV_ROUND_UP(q_data->height, 16)) * 3200 / 8 + 512;
P
Philipp Zabel 已提交
400 401
		ret = coda_alloc_context_buf(ctx, &ctx->slicebuf, size,
					     "slicebuf");
402
		if (ret < 0) {
P
Philipp Zabel 已提交
403 404
			v4l2_err(&dev->v4l2_dev,
				 "failed to allocate %d byte slice buffer",
405 406 407 408 409 410
				 ctx->slicebuf.size);
			return ret;
		}
	}

	if (dev->devtype->product == CODA_7541) {
P
Philipp Zabel 已提交
411 412
		ret = coda_alloc_context_buf(ctx, &ctx->psbuf,
					     CODA7_PS_BUF_SIZE, "psbuf");
413
		if (ret < 0) {
P
Philipp Zabel 已提交
414 415
			v4l2_err(&dev->v4l2_dev,
				 "failed to allocate psmem buffer");
416 417 418 419 420 421 422 423 424 425
			goto err;
		}
	}

	size = dev->devtype->workbuf_size;
	if (dev->devtype->product == CODA_960 &&
	    q_data->fourcc == V4L2_PIX_FMT_H264)
		size += CODA9_PS_SAVE_SIZE;
	ret = coda_alloc_context_buf(ctx, &ctx->workbuf, size, "workbuf");
	if (ret < 0) {
P
Philipp Zabel 已提交
426 427
		v4l2_err(&dev->v4l2_dev,
			 "failed to allocate %d byte context buffer",
428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495
			 ctx->workbuf.size);
		goto err;
	}

	return 0;

err:
	coda_free_context_buffers(ctx);
	return ret;
}

static int coda_encode_header(struct coda_ctx *ctx, struct vb2_buffer *buf,
			      int header_code, u8 *header, int *size)
{
	struct coda_dev *dev = ctx->dev;
	size_t bufsize;
	int ret;
	int i;

	if (dev->devtype->product == CODA_960)
		memset(vb2_plane_vaddr(buf, 0), 0, 64);

	coda_write(dev, vb2_dma_contig_plane_dma_addr(buf, 0),
		   CODA_CMD_ENC_HEADER_BB_START);
	bufsize = vb2_plane_size(buf, 0);
	if (dev->devtype->product == CODA_960)
		bufsize /= 1024;
	coda_write(dev, bufsize, CODA_CMD_ENC_HEADER_BB_SIZE);
	coda_write(dev, header_code, CODA_CMD_ENC_HEADER_CODE);
	ret = coda_command_sync(ctx, CODA_COMMAND_ENCODE_HEADER);
	if (ret < 0) {
		v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_ENCODE_HEADER timeout\n");
		return ret;
	}

	if (dev->devtype->product == CODA_960) {
		for (i = 63; i > 0; i--)
			if (((char *)vb2_plane_vaddr(buf, 0))[i] != 0)
				break;
		*size = i + 1;
	} else {
		*size = coda_read(dev, CODA_REG_BIT_WR_PTR(ctx->reg_idx)) -
			coda_read(dev, CODA_CMD_ENC_HEADER_BB_START);
	}
	memcpy(header, vb2_plane_vaddr(buf, 0), *size);

	return 0;
}

static phys_addr_t coda_iram_alloc(struct coda_iram_info *iram, size_t size)
{
	phys_addr_t ret;

	size = round_up(size, 1024);
	if (size > iram->remaining)
		return 0;
	iram->remaining -= size;

	ret = iram->next_paddr;
	iram->next_paddr += size;

	return ret;
}

static void coda_setup_iram(struct coda_ctx *ctx)
{
	struct coda_iram_info *iram_info = &ctx->iram_info;
	struct coda_dev *dev = ctx->dev;
P
Philipp Zabel 已提交
496
	int w64, w128;
497 498 499 500 501 502 503 504 505
	int mb_width;
	int dbk_bits;
	int bit_bits;
	int ip_bits;

	memset(iram_info, 0, sizeof(*iram_info));
	iram_info->next_paddr = dev->iram.paddr;
	iram_info->remaining = dev->iram.size;

506 507 508
	if (!dev->iram.vaddr)
		return;

509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528
	switch (dev->devtype->product) {
	case CODA_7541:
		dbk_bits = CODA7_USE_HOST_DBK_ENABLE | CODA7_USE_DBK_ENABLE;
		bit_bits = CODA7_USE_HOST_BIT_ENABLE | CODA7_USE_BIT_ENABLE;
		ip_bits = CODA7_USE_HOST_IP_ENABLE | CODA7_USE_IP_ENABLE;
		break;
	case CODA_960:
		dbk_bits = CODA9_USE_HOST_DBK_ENABLE | CODA9_USE_DBK_ENABLE;
		bit_bits = CODA9_USE_HOST_BIT_ENABLE | CODA7_USE_BIT_ENABLE;
		ip_bits = CODA9_USE_HOST_IP_ENABLE | CODA7_USE_IP_ENABLE;
		break;
	default: /* CODA_DX6 */
		return;
	}

	if (ctx->inst_type == CODA_INST_ENCODER) {
		struct coda_q_data *q_data_src;

		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
		mb_width = DIV_ROUND_UP(q_data_src->width, 16);
P
Philipp Zabel 已提交
529 530
		w128 = mb_width * 128;
		w64 = mb_width * 64;
531 532 533 534 535 536

		/* Prioritize in case IRAM is too small for everything */
		if (dev->devtype->product == CODA_7541) {
			iram_info->search_ram_size = round_up(mb_width * 16 *
							      36 + 2048, 1024);
			iram_info->search_ram_paddr = coda_iram_alloc(iram_info,
P
Philipp Zabel 已提交
537
						iram_info->search_ram_size);
538 539 540 541 542 543 544 545 546
			if (!iram_info->search_ram_paddr) {
				pr_err("IRAM is smaller than the search ram size\n");
				goto out;
			}
			iram_info->axi_sram_use |= CODA7_USE_HOST_ME_ENABLE |
						   CODA7_USE_ME_ENABLE;
		}

		/* Only H.264BP and H.263P3 are considered */
P
Philipp Zabel 已提交
547 548
		iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, w64);
		iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, w64);
549 550 551 552
		if (!iram_info->buf_dbk_c_use)
			goto out;
		iram_info->axi_sram_use |= dbk_bits;

P
Philipp Zabel 已提交
553
		iram_info->buf_bit_use = coda_iram_alloc(iram_info, w128);
554 555 556 557
		if (!iram_info->buf_bit_use)
			goto out;
		iram_info->axi_sram_use |= bit_bits;

P
Philipp Zabel 已提交
558
		iram_info->buf_ip_ac_dc_use = coda_iram_alloc(iram_info, w128);
559 560 561 562 563 564 565 566 567 568
		if (!iram_info->buf_ip_ac_dc_use)
			goto out;
		iram_info->axi_sram_use |= ip_bits;

		/* OVL and BTP disabled for encoder */
	} else if (ctx->inst_type == CODA_INST_DECODER) {
		struct coda_q_data *q_data_dst;

		q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
		mb_width = DIV_ROUND_UP(q_data_dst->width, 16);
P
Philipp Zabel 已提交
569
		w128 = mb_width * 128;
570

P
Philipp Zabel 已提交
571 572
		iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, w128);
		iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, w128);
573 574 575 576
		if (!iram_info->buf_dbk_c_use)
			goto out;
		iram_info->axi_sram_use |= dbk_bits;

P
Philipp Zabel 已提交
577
		iram_info->buf_bit_use = coda_iram_alloc(iram_info, w128);
578 579 580 581
		if (!iram_info->buf_bit_use)
			goto out;
		iram_info->axi_sram_use |= bit_bits;

P
Philipp Zabel 已提交
582
		iram_info->buf_ip_ac_dc_use = coda_iram_alloc(iram_info, w128);
583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668
		if (!iram_info->buf_ip_ac_dc_use)
			goto out;
		iram_info->axi_sram_use |= ip_bits;

		/* OVL and BTP unused as there is no VC1 support yet */
	}

out:
	if (!(iram_info->axi_sram_use & CODA7_USE_HOST_IP_ENABLE))
		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
			 "IRAM smaller than needed\n");

	if (dev->devtype->product == CODA_7541) {
		/* TODO - Enabling these causes picture errors on CODA7541 */
		if (ctx->inst_type == CODA_INST_DECODER) {
			/* fw 1.4.50 */
			iram_info->axi_sram_use &= ~(CODA7_USE_HOST_IP_ENABLE |
						     CODA7_USE_IP_ENABLE);
		} else {
			/* fw 13.4.29 */
			iram_info->axi_sram_use &= ~(CODA7_USE_HOST_IP_ENABLE |
						     CODA7_USE_HOST_DBK_ENABLE |
						     CODA7_USE_IP_ENABLE |
						     CODA7_USE_DBK_ENABLE);
		}
	}
}

static u32 coda_supported_firmwares[] = {
	CODA_FIRMWARE_VERNUM(CODA_DX6, 2, 2, 5),
	CODA_FIRMWARE_VERNUM(CODA_7541, 1, 4, 50),
	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 5),
};

static bool coda_firmware_supported(u32 vernum)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(coda_supported_firmwares); i++)
		if (vernum == coda_supported_firmwares[i])
			return true;
	return false;
}

int coda_check_firmware(struct coda_dev *dev)
{
	u16 product, major, minor, release;
	u32 data;
	int ret;

	ret = clk_prepare_enable(dev->clk_per);
	if (ret)
		goto err_clk_per;

	ret = clk_prepare_enable(dev->clk_ahb);
	if (ret)
		goto err_clk_ahb;

	coda_write(dev, 0, CODA_CMD_FIRMWARE_VERNUM);
	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
	coda_write(dev, 0, CODA_REG_BIT_RUN_INDEX);
	coda_write(dev, 0, CODA_REG_BIT_RUN_COD_STD);
	coda_write(dev, CODA_COMMAND_FIRMWARE_GET, CODA_REG_BIT_RUN_COMMAND);
	if (coda_wait_timeout(dev)) {
		v4l2_err(&dev->v4l2_dev, "firmware get command error\n");
		ret = -EIO;
		goto err_run_cmd;
	}

	if (dev->devtype->product == CODA_960) {
		data = coda_read(dev, CODA9_CMD_FIRMWARE_CODE_REV);
		v4l2_info(&dev->v4l2_dev, "Firmware code revision: %d\n",
			  data);
	}

	/* Check we are compatible with the loaded firmware */
	data = coda_read(dev, CODA_CMD_FIRMWARE_VERNUM);
	product = CODA_FIRMWARE_PRODUCT(data);
	major = CODA_FIRMWARE_MAJOR(data);
	minor = CODA_FIRMWARE_MINOR(data);
	release = CODA_FIRMWARE_RELEASE(data);

	clk_disable_unprepare(dev->clk_per);
	clk_disable_unprepare(dev->clk_ahb);

	if (product != dev->devtype->product) {
P
Philipp Zabel 已提交
669 670
		v4l2_err(&dev->v4l2_dev,
			 "Wrong firmware. Hw: %s, Fw: %s, Version: %u.%u.%u\n",
671 672 673 674 675 676 677 678 679 680 681 682
			 coda_product_name(dev->devtype->product),
			 coda_product_name(product), major, minor, release);
		return -EINVAL;
	}

	v4l2_info(&dev->v4l2_dev, "Initialized %s.\n",
		  coda_product_name(product));

	if (coda_firmware_supported(data)) {
		v4l2_info(&dev->v4l2_dev, "Firmware version: %u.%u.%u\n",
			  major, minor, release);
	} else {
P
Philipp Zabel 已提交
683 684 685
		v4l2_warn(&dev->v4l2_dev,
			  "Unsupported firmware version: %u.%u.%u\n",
			  major, minor, release);
686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
	}

	return 0;

err_run_cmd:
	clk_disable_unprepare(dev->clk_ahb);
err_clk_ahb:
	clk_disable_unprepare(dev->clk_per);
err_clk_per:
	return ret;
}

/*
 * Encoder context operations
 */

static int coda_start_encoding(struct coda_ctx *ctx)
{
	struct coda_dev *dev = ctx->dev;
	struct v4l2_device *v4l2_dev = &dev->v4l2_dev;
	struct coda_q_data *q_data_src, *q_data_dst;
	u32 bitstream_buf, bitstream_size;
	struct vb2_buffer *buf;
	int gamma, ret, value;
	u32 dst_fourcc;
711
	u32 stride;
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730

	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
	dst_fourcc = q_data_dst->fourcc;

	/* Allocate per-instance buffers */
	ret = coda_alloc_context_buffers(ctx, q_data_src);
	if (ret < 0)
		return ret;

	buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
	bitstream_buf = vb2_dma_contig_plane_dma_addr(buf, 0);
	bitstream_size = q_data_dst->sizeimage;

	if (!coda_is_initialized(dev)) {
		v4l2_err(v4l2_dev, "coda is not initialized.\n");
		return -EFAULT;
	}

731 732 733 734 735 736 737 738
	if (dst_fourcc == V4L2_PIX_FMT_JPEG) {
		if (!ctx->params.jpeg_qmat_tab[0])
			ctx->params.jpeg_qmat_tab[0] = kmalloc(64, GFP_KERNEL);
		if (!ctx->params.jpeg_qmat_tab[1])
			ctx->params.jpeg_qmat_tab[1] = kmalloc(64, GFP_KERNEL);
		coda_set_jpeg_compression_quality(ctx, ctx->params.jpeg_quality);
	}

739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757
	mutex_lock(&dev->coda_mutex);

	coda_write(dev, ctx->parabuf.paddr, CODA_REG_BIT_PARA_BUF_ADDR);
	coda_write(dev, bitstream_buf, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
	coda_write(dev, bitstream_buf, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
	switch (dev->devtype->product) {
	case CODA_DX6:
		coda_write(dev, CODADX6_STREAM_BUF_DYNALLOC_EN |
			CODADX6_STREAM_BUF_PIC_RESET, CODA_REG_BIT_STREAM_CTRL);
		break;
	case CODA_960:
		coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
		/* fallthrough */
	case CODA_7541:
		coda_write(dev, CODA7_STREAM_BUF_DYNALLOC_EN |
			CODA7_STREAM_BUF_PIC_RESET, CODA_REG_BIT_STREAM_CTRL);
		break;
	}

758 759 760
	ctx->frame_mem_ctrl &= ~CODA_FRAME_CHROMA_INTERLEAVE;
	if (q_data_src->fourcc == V4L2_PIX_FMT_NV12)
		ctx->frame_mem_ctrl |= CODA_FRAME_CHROMA_INTERLEAVE;
761
	coda_write(dev, ctx->frame_mem_ctrl, CODA_REG_BIT_FRAME_MEM_CTRL);
762 763 764

	if (dev->devtype->product == CODA_DX6) {
		/* Configure the coda */
P
Philipp Zabel 已提交
765 766
		coda_write(dev, dev->iram.paddr,
			   CODADX6_REG_BIT_SEARCH_RAM_BASE_ADDR);
767 768 769
	}

	/* Could set rotation here if needed */
770
	value = 0;
771 772
	switch (dev->devtype->product) {
	case CODA_DX6:
P
Philipp Zabel 已提交
773 774 775 776
		value = (q_data_src->width & CODADX6_PICWIDTH_MASK)
			<< CODADX6_PICWIDTH_OFFSET;
		value |= (q_data_src->height & CODADX6_PICHEIGHT_MASK)
			 << CODA_PICHEIGHT_OFFSET;
777 778 779 780 781 782
		break;
	case CODA_7541:
		if (dst_fourcc == V4L2_PIX_FMT_H264) {
			value = (round_up(q_data_src->width, 16) &
				 CODA7_PICWIDTH_MASK) << CODA7_PICWIDTH_OFFSET;
			value |= (round_up(q_data_src->height, 16) &
P
Philipp Zabel 已提交
783
				 CODA7_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
784 785 786 787
			break;
		}
		/* fallthrough */
	case CODA_960:
P
Philipp Zabel 已提交
788 789 790 791
		value = (q_data_src->width & CODA7_PICWIDTH_MASK)
			<< CODA7_PICWIDTH_OFFSET;
		value |= (q_data_src->height & CODA7_PICHEIGHT_MASK)
			 << CODA_PICHEIGHT_OFFSET;
792 793
	}
	coda_write(dev, value, CODA_CMD_ENC_SEQ_SRC_SIZE);
794 795
	if (dst_fourcc == V4L2_PIX_FMT_JPEG)
		ctx->params.framerate = 0;
796 797 798 799 800 801 802
	coda_write(dev, ctx->params.framerate,
		   CODA_CMD_ENC_SEQ_SRC_F_RATE);

	ctx->params.codec_mode = ctx->codec->mode;
	switch (dst_fourcc) {
	case V4L2_PIX_FMT_MPEG4:
		if (dev->devtype->product == CODA_960)
P
Philipp Zabel 已提交
803 804
			coda_write(dev, CODA9_STD_MPEG4,
				   CODA_CMD_ENC_SEQ_COD_STD);
805
		else
P
Philipp Zabel 已提交
806 807
			coda_write(dev, CODA_STD_MPEG4,
				   CODA_CMD_ENC_SEQ_COD_STD);
808 809 810 811
		coda_write(dev, 0, CODA_CMD_ENC_SEQ_MP4_PARA);
		break;
	case V4L2_PIX_FMT_H264:
		if (dev->devtype->product == CODA_960)
P
Philipp Zabel 已提交
812 813
			coda_write(dev, CODA9_STD_H264,
				   CODA_CMD_ENC_SEQ_COD_STD);
814
		else
P
Philipp Zabel 已提交
815 816
			coda_write(dev, CODA_STD_H264,
				   CODA_CMD_ENC_SEQ_COD_STD);
817 818 819 820 821 822 823 824 825 826 827 828
		if (ctx->params.h264_deblk_enabled) {
			value = ((ctx->params.h264_deblk_alpha &
				  CODA_264PARAM_DEBLKFILTEROFFSETALPHA_MASK) <<
				 CODA_264PARAM_DEBLKFILTEROFFSETALPHA_OFFSET) |
				((ctx->params.h264_deblk_beta &
				  CODA_264PARAM_DEBLKFILTEROFFSETBETA_MASK) <<
				 CODA_264PARAM_DEBLKFILTEROFFSETBETA_OFFSET);
		} else {
			value = 1 << CODA_264PARAM_DISABLEDEBLK_OFFSET;
		}
		coda_write(dev, value, CODA_CMD_ENC_SEQ_264_PARA);
		break;
829 830 831 832 833 834 835 836 837 838
	case V4L2_PIX_FMT_JPEG:
		coda_write(dev, 0, CODA_CMD_ENC_SEQ_JPG_PARA);
		coda_write(dev, ctx->params.jpeg_restart_interval,
				CODA_CMD_ENC_SEQ_JPG_RST_INTERVAL);
		coda_write(dev, 0, CODA_CMD_ENC_SEQ_JPG_THUMB_EN);
		coda_write(dev, 0, CODA_CMD_ENC_SEQ_JPG_THUMB_SIZE);
		coda_write(dev, 0, CODA_CMD_ENC_SEQ_JPG_THUMB_OFFSET);

		coda_jpeg_write_tables(ctx);
		break;
839 840 841 842 843 844 845
	default:
		v4l2_err(v4l2_dev,
			 "dst format (0x%08x) invalid.\n", dst_fourcc);
		ret = -EINVAL;
		goto out;
	}

846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874
	/*
	 * slice mode and GOP size registers are used for thumb size/offset
	 * in JPEG mode
	 */
	if (dst_fourcc != V4L2_PIX_FMT_JPEG) {
		switch (ctx->params.slice_mode) {
		case V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE:
			value = 0;
			break;
		case V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_MB:
			value  = (ctx->params.slice_max_mb &
				  CODA_SLICING_SIZE_MASK)
				 << CODA_SLICING_SIZE_OFFSET;
			value |= (1 & CODA_SLICING_UNIT_MASK)
				 << CODA_SLICING_UNIT_OFFSET;
			value |=  1 & CODA_SLICING_MODE_MASK;
			break;
		case V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES:
			value  = (ctx->params.slice_max_bits &
				  CODA_SLICING_SIZE_MASK)
				 << CODA_SLICING_SIZE_OFFSET;
			value |= (0 & CODA_SLICING_UNIT_MASK)
				 << CODA_SLICING_UNIT_OFFSET;
			value |=  1 & CODA_SLICING_MODE_MASK;
			break;
		}
		coda_write(dev, value, CODA_CMD_ENC_SEQ_SLICE_MODE);
		value = ctx->params.gop_size & CODA_GOP_SIZE_MASK;
		coda_write(dev, value, CODA_CMD_ENC_SEQ_GOP_SIZE);
875 876 877 878
	}

	if (ctx->params.bitrate) {
		/* Rate control enabled */
P
Philipp Zabel 已提交
879 880
		value = (ctx->params.bitrate & CODA_RATECONTROL_BITRATE_MASK)
			<< CODA_RATECONTROL_BITRATE_OFFSET;
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965
		value |=  1 & CODA_RATECONTROL_ENABLE_MASK;
		if (dev->devtype->product == CODA_960)
			value |= BIT(31); /* disable autoskip */
	} else {
		value = 0;
	}
	coda_write(dev, value, CODA_CMD_ENC_SEQ_RC_PARA);

	coda_write(dev, 0, CODA_CMD_ENC_SEQ_RC_BUF_SIZE);
	coda_write(dev, ctx->params.intra_refresh,
		   CODA_CMD_ENC_SEQ_INTRA_REFRESH);

	coda_write(dev, bitstream_buf, CODA_CMD_ENC_SEQ_BB_START);
	coda_write(dev, bitstream_size / 1024, CODA_CMD_ENC_SEQ_BB_SIZE);


	value = 0;
	if (dev->devtype->product == CODA_960)
		gamma = CODA9_DEFAULT_GAMMA;
	else
		gamma = CODA_DEFAULT_GAMMA;
	if (gamma > 0) {
		coda_write(dev, (gamma & CODA_GAMMA_MASK) << CODA_GAMMA_OFFSET,
			   CODA_CMD_ENC_SEQ_RC_GAMMA);
	}

	if (ctx->params.h264_min_qp || ctx->params.h264_max_qp) {
		coda_write(dev,
			   ctx->params.h264_min_qp << CODA_QPMIN_OFFSET |
			   ctx->params.h264_max_qp << CODA_QPMAX_OFFSET,
			   CODA_CMD_ENC_SEQ_RC_QP_MIN_MAX);
	}
	if (dev->devtype->product == CODA_960) {
		if (ctx->params.h264_max_qp)
			value |= 1 << CODA9_OPTION_RCQPMAX_OFFSET;
		if (CODA_DEFAULT_GAMMA > 0)
			value |= 1 << CODA9_OPTION_GAMMA_OFFSET;
	} else {
		if (CODA_DEFAULT_GAMMA > 0) {
			if (dev->devtype->product == CODA_DX6)
				value |= 1 << CODADX6_OPTION_GAMMA_OFFSET;
			else
				value |= 1 << CODA7_OPTION_GAMMA_OFFSET;
		}
		if (ctx->params.h264_min_qp)
			value |= 1 << CODA7_OPTION_RCQPMIN_OFFSET;
		if (ctx->params.h264_max_qp)
			value |= 1 << CODA7_OPTION_RCQPMAX_OFFSET;
	}
	coda_write(dev, value, CODA_CMD_ENC_SEQ_OPTION);

	coda_write(dev, 0, CODA_CMD_ENC_SEQ_RC_INTERVAL_MODE);

	coda_setup_iram(ctx);

	if (dst_fourcc == V4L2_PIX_FMT_H264) {
		switch (dev->devtype->product) {
		case CODA_DX6:
			value = FMO_SLICE_SAVE_BUF_SIZE << 7;
			coda_write(dev, value, CODADX6_CMD_ENC_SEQ_FMO);
			break;
		case CODA_7541:
			coda_write(dev, ctx->iram_info.search_ram_paddr,
					CODA7_CMD_ENC_SEQ_SEARCH_BASE);
			coda_write(dev, ctx->iram_info.search_ram_size,
					CODA7_CMD_ENC_SEQ_SEARCH_SIZE);
			break;
		case CODA_960:
			coda_write(dev, 0, CODA9_CMD_ENC_SEQ_ME_OPTION);
			coda_write(dev, 0, CODA9_CMD_ENC_SEQ_INTRA_WEIGHT);
		}
	}

	ret = coda_command_sync(ctx, CODA_COMMAND_SEQ_INIT);
	if (ret < 0) {
		v4l2_err(v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
		goto out;
	}

	if (coda_read(dev, CODA_RET_ENC_SEQ_SUCCESS) == 0) {
		v4l2_err(v4l2_dev, "CODA_COMMAND_SEQ_INIT failed\n");
		ret = -EFAULT;
		goto out;
	}

966 967 968 969 970 971 972 973 974 975 976 977 978 979
	if (dst_fourcc != V4L2_PIX_FMT_JPEG) {
		if (dev->devtype->product == CODA_960)
			ctx->num_internal_frames = 4;
		else
			ctx->num_internal_frames = 2;
		ret = coda_alloc_framebuffers(ctx, q_data_src, dst_fourcc);
		if (ret < 0) {
			v4l2_err(v4l2_dev, "failed to allocate framebuffers\n");
			goto out;
		}
		stride = q_data_src->bytesperline;
	} else {
		ctx->num_internal_frames = 0;
		stride = 0;
980 981
	}
	coda_write(dev, ctx->num_internal_frames, CODA_CMD_SET_FRAME_BUF_NUM);
982 983
	coda_write(dev, stride, CODA_CMD_SET_FRAME_BUF_STRIDE);

984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003
	if (dev->devtype->product == CODA_7541) {
		coda_write(dev, q_data_src->bytesperline,
				CODA7_CMD_SET_FRAME_SOURCE_BUF_STRIDE);
	}
	if (dev->devtype->product != CODA_DX6) {
		coda_write(dev, ctx->iram_info.buf_bit_use,
				CODA7_CMD_SET_FRAME_AXI_BIT_ADDR);
		coda_write(dev, ctx->iram_info.buf_ip_ac_dc_use,
				CODA7_CMD_SET_FRAME_AXI_IPACDC_ADDR);
		coda_write(dev, ctx->iram_info.buf_dbk_y_use,
				CODA7_CMD_SET_FRAME_AXI_DBKY_ADDR);
		coda_write(dev, ctx->iram_info.buf_dbk_c_use,
				CODA7_CMD_SET_FRAME_AXI_DBKC_ADDR);
		coda_write(dev, ctx->iram_info.buf_ovl_use,
				CODA7_CMD_SET_FRAME_AXI_OVL_ADDR);
		if (dev->devtype->product == CODA_960) {
			coda_write(dev, ctx->iram_info.buf_btp_use,
					CODA9_CMD_SET_FRAME_AXI_BTP_ADDR);

			/* FIXME */
P
Philipp Zabel 已提交
1004 1005 1006 1007
			coda_write(dev, ctx->internal_frames[2].paddr,
				   CODA9_CMD_SET_FRAME_SUBSAMP_A);
			coda_write(dev, ctx->internal_frames[3].paddr,
				   CODA9_CMD_SET_FRAME_SUBSAMP_B);
1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091
		}
	}

	ret = coda_command_sync(ctx, CODA_COMMAND_SET_FRAME_BUF);
	if (ret < 0) {
		v4l2_err(v4l2_dev, "CODA_COMMAND_SET_FRAME_BUF timeout\n");
		goto out;
	}

	/* Save stream headers */
	buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
	switch (dst_fourcc) {
	case V4L2_PIX_FMT_H264:
		/*
		 * Get SPS in the first frame and copy it to an
		 * intermediate buffer.
		 */
		ret = coda_encode_header(ctx, buf, CODA_HEADER_H264_SPS,
					 &ctx->vpu_header[0][0],
					 &ctx->vpu_header_size[0]);
		if (ret < 0)
			goto out;

		/*
		 * Get PPS in the first frame and copy it to an
		 * intermediate buffer.
		 */
		ret = coda_encode_header(ctx, buf, CODA_HEADER_H264_PPS,
					 &ctx->vpu_header[1][0],
					 &ctx->vpu_header_size[1]);
		if (ret < 0)
			goto out;

		/*
		 * Length of H.264 headers is variable and thus it might not be
		 * aligned for the coda to append the encoded frame. In that is
		 * the case a filler NAL must be added to header 2.
		 */
		ctx->vpu_header_size[2] = coda_h264_padding(
					(ctx->vpu_header_size[0] +
					 ctx->vpu_header_size[1]),
					 ctx->vpu_header[2]);
		break;
	case V4L2_PIX_FMT_MPEG4:
		/*
		 * Get VOS in the first frame and copy it to an
		 * intermediate buffer
		 */
		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VOS,
					 &ctx->vpu_header[0][0],
					 &ctx->vpu_header_size[0]);
		if (ret < 0)
			goto out;

		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VIS,
					 &ctx->vpu_header[1][0],
					 &ctx->vpu_header_size[1]);
		if (ret < 0)
			goto out;

		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VOL,
					 &ctx->vpu_header[2][0],
					 &ctx->vpu_header_size[2]);
		if (ret < 0)
			goto out;
		break;
	default:
		/* No more formats need to save headers at the moment */
		break;
	}

out:
	mutex_unlock(&dev->coda_mutex);
	return ret;
}

static int coda_prepare_encode(struct coda_ctx *ctx)
{
	struct coda_q_data *q_data_src, *q_data_dst;
	struct vb2_buffer *src_buf, *dst_buf;
	struct coda_dev *dev = ctx->dev;
	int force_ipicture;
	int quant_param = 0;
	u32 pic_stream_buffer_addr, pic_stream_buffer_size;
1092
	u32 rot_mode = 0;
1093
	u32 dst_fourcc;
1094
	u32 reg;
1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131

	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
	dst_fourcc = q_data_dst->fourcc;

	src_buf->v4l2_buf.sequence = ctx->osequence;
	dst_buf->v4l2_buf.sequence = ctx->osequence;
	ctx->osequence++;

	/*
	 * Workaround coda firmware BUG that only marks the first
	 * frame as IDR. This is a problem for some decoders that can't
	 * recover when a frame is lost.
	 */
	if (src_buf->v4l2_buf.sequence % ctx->params.gop_size) {
		src_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_PFRAME;
		src_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_KEYFRAME;
	} else {
		src_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_KEYFRAME;
		src_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_PFRAME;
	}

	if (dev->devtype->product == CODA_960)
		coda_set_gdi_regs(ctx);

	/*
	 * Copy headers at the beginning of the first frame for H.264 only.
	 * In MPEG4 they are already copied by the coda.
	 */
	if (src_buf->v4l2_buf.sequence == 0) {
		pic_stream_buffer_addr =
			vb2_dma_contig_plane_dma_addr(dst_buf, 0) +
			ctx->vpu_header_size[0] +
			ctx->vpu_header_size[1] +
			ctx->vpu_header_size[2];
1132
		pic_stream_buffer_size = q_data_dst->sizeimage -
1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
			ctx->vpu_header_size[0] -
			ctx->vpu_header_size[1] -
			ctx->vpu_header_size[2];
		memcpy(vb2_plane_vaddr(dst_buf, 0),
		       &ctx->vpu_header[0][0], ctx->vpu_header_size[0]);
		memcpy(vb2_plane_vaddr(dst_buf, 0) + ctx->vpu_header_size[0],
		       &ctx->vpu_header[1][0], ctx->vpu_header_size[1]);
		memcpy(vb2_plane_vaddr(dst_buf, 0) + ctx->vpu_header_size[0] +
			ctx->vpu_header_size[1], &ctx->vpu_header[2][0],
			ctx->vpu_header_size[2]);
	} else {
		pic_stream_buffer_addr =
			vb2_dma_contig_plane_dma_addr(dst_buf, 0);
1146
		pic_stream_buffer_size = q_data_dst->sizeimage;
1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157
	}

	if (src_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) {
		force_ipicture = 1;
		switch (dst_fourcc) {
		case V4L2_PIX_FMT_H264:
			quant_param = ctx->params.h264_intra_qp;
			break;
		case V4L2_PIX_FMT_MPEG4:
			quant_param = ctx->params.mpeg4_intra_qp;
			break;
1158 1159 1160
		case V4L2_PIX_FMT_JPEG:
			quant_param = 30;
			break;
1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182
		default:
			v4l2_warn(&ctx->dev->v4l2_dev,
				"cannot set intra qp, fmt not supported\n");
			break;
		}
	} else {
		force_ipicture = 0;
		switch (dst_fourcc) {
		case V4L2_PIX_FMT_H264:
			quant_param = ctx->params.h264_inter_qp;
			break;
		case V4L2_PIX_FMT_MPEG4:
			quant_param = ctx->params.mpeg4_inter_qp;
			break;
		default:
			v4l2_warn(&ctx->dev->v4l2_dev,
				"cannot set inter qp, fmt not supported\n");
			break;
		}
	}

	/* submit */
1183 1184 1185
	if (ctx->params.rot_mode)
		rot_mode = CODA_ROT_MIR_ENABLE | ctx->params.rot_mode;
	coda_write(dev, rot_mode, CODA_CMD_ENC_PIC_ROT_MODE);
1186 1187 1188 1189 1190 1191 1192
	coda_write(dev, quant_param, CODA_CMD_ENC_PIC_QS);

	if (dev->devtype->product == CODA_960) {
		coda_write(dev, 4/*FIXME: 0*/, CODA9_CMD_ENC_PIC_SRC_INDEX);
		coda_write(dev, q_data_src->width, CODA9_CMD_ENC_PIC_SRC_STRIDE);
		coda_write(dev, 0, CODA9_CMD_ENC_PIC_SUB_FRAME_SYNC);

1193
		reg = CODA9_CMD_ENC_PIC_SRC_ADDR_Y;
1194
	} else {
1195
		reg = CODA_CMD_ENC_PIC_SRC_ADDR_Y;
1196
	}
1197 1198
	coda_write_base(ctx, q_data_src, src_buf, reg);

1199 1200 1201 1202 1203 1204 1205 1206
	coda_write(dev, force_ipicture << 1 & 0x2,
		   CODA_CMD_ENC_PIC_OPTION);

	coda_write(dev, pic_stream_buffer_addr, CODA_CMD_ENC_PIC_BB_START);
	coda_write(dev, pic_stream_buffer_size / 1024,
		   CODA_CMD_ENC_PIC_BB_SIZE);

	if (!ctx->streamon_out) {
P
Philipp Zabel 已提交
1207
		/* After streamoff on the output side, set stream end flag */
1208
		ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
P
Philipp Zabel 已提交
1209 1210
		coda_write(dev, ctx->bit_stream_param,
			   CODA_REG_BIT_BIT_STREAM_PARAM);
1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289
	}

	if (dev->devtype->product != CODA_DX6)
		coda_write(dev, ctx->iram_info.axi_sram_use,
				CODA7_REG_BIT_AXI_SRAM_USE);

	coda_command_async(ctx, CODA_COMMAND_PIC_RUN);

	return 0;
}

static void coda_finish_encode(struct coda_ctx *ctx)
{
	struct vb2_buffer *src_buf, *dst_buf;
	struct coda_dev *dev = ctx->dev;
	u32 wr_ptr, start_ptr;

	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);

	/* Get results from the coda */
	start_ptr = coda_read(dev, CODA_CMD_ENC_PIC_BB_START);
	wr_ptr = coda_read(dev, CODA_REG_BIT_WR_PTR(ctx->reg_idx));

	/* Calculate bytesused field */
	if (dst_buf->v4l2_buf.sequence == 0) {
		vb2_set_plane_payload(dst_buf, 0, wr_ptr - start_ptr +
					ctx->vpu_header_size[0] +
					ctx->vpu_header_size[1] +
					ctx->vpu_header_size[2]);
	} else {
		vb2_set_plane_payload(dst_buf, 0, wr_ptr - start_ptr);
	}

	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "frame size = %u\n",
		 wr_ptr - start_ptr);

	coda_read(dev, CODA_RET_ENC_PIC_SLICE_NUM);
	coda_read(dev, CODA_RET_ENC_PIC_FLAG);

	if (coda_read(dev, CODA_RET_ENC_PIC_TYPE) == 0) {
		dst_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_KEYFRAME;
		dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_PFRAME;
	} else {
		dst_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_PFRAME;
		dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_KEYFRAME;
	}

	dst_buf->v4l2_buf.timestamp = src_buf->v4l2_buf.timestamp;
	dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
	dst_buf->v4l2_buf.flags |=
		src_buf->v4l2_buf.flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
	dst_buf->v4l2_buf.timecode = src_buf->v4l2_buf.timecode;

	v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);

	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
	v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE);

	ctx->gopcounter--;
	if (ctx->gopcounter < 0)
		ctx->gopcounter = ctx->params.gop_size - 1;

	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
		"job finished: encoding frame (%d) (%s)\n",
		dst_buf->v4l2_buf.sequence,
		(dst_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) ?
		"KEYFRAME" : "PFRAME");
}

static void coda_seq_end_work(struct work_struct *work)
{
	struct coda_ctx *ctx = container_of(work, struct coda_ctx, seq_end_work);
	struct coda_dev *dev = ctx->dev;

	mutex_lock(&ctx->buffer_mutex);
	mutex_lock(&dev->coda_mutex);

	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
P
Philipp Zabel 已提交
1290 1291
		 "%d: %s: sent command 'SEQ_END' to coda\n", ctx->idx,
		 __func__);
1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331
	if (coda_command_sync(ctx, CODA_COMMAND_SEQ_END)) {
		v4l2_err(&dev->v4l2_dev,
			 "CODA_COMMAND_SEQ_END failed\n");
	}

	kfifo_init(&ctx->bitstream_fifo,
		ctx->bitstream.vaddr, ctx->bitstream.size);

	coda_free_framebuffers(ctx);
	coda_free_context_buffers(ctx);

	mutex_unlock(&dev->coda_mutex);
	mutex_unlock(&ctx->buffer_mutex);
}

static void coda_bit_release(struct coda_ctx *ctx)
{
	coda_free_framebuffers(ctx);
	coda_free_context_buffers(ctx);
}

const struct coda_context_ops coda_bit_encode_ops = {
	.queue_init = coda_encoder_queue_init,
	.start_streaming = coda_start_encoding,
	.prepare_run = coda_prepare_encode,
	.finish_run = coda_finish_encode,
	.seq_end_work = coda_seq_end_work,
	.release = coda_bit_release,
};

/*
 * Decoder context operations
 */

static int __coda_start_decoding(struct coda_ctx *ctx)
{
	struct coda_q_data *q_data_src, *q_data_dst;
	u32 bitstream_buf, bitstream_size;
	struct coda_dev *dev = ctx->dev;
	int width, height;
1332
	u32 src_fourcc, dst_fourcc;
1333 1334 1335 1336 1337 1338 1339 1340 1341
	u32 val;
	int ret;

	/* Start decoding */
	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
	bitstream_buf = ctx->bitstream.paddr;
	bitstream_size = ctx->bitstream.size;
	src_fourcc = q_data_src->fourcc;
1342
	dst_fourcc = q_data_dst->fourcc;
1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353

	/* Allocate per-instance buffers */
	ret = coda_alloc_context_buffers(ctx, q_data_src);
	if (ret < 0)
		return ret;

	coda_write(dev, ctx->parabuf.paddr, CODA_REG_BIT_PARA_BUF_ADDR);

	/* Update coda bitstream read and write pointers from kfifo */
	coda_kfifo_sync_to_device_full(ctx);

1354 1355 1356
	ctx->frame_mem_ctrl &= ~CODA_FRAME_CHROMA_INTERLEAVE;
	if (dst_fourcc == V4L2_PIX_FMT_NV12)
		ctx->frame_mem_ctrl |= CODA_FRAME_CHROMA_INTERLEAVE;
1357 1358
	coda_write(dev, ctx->frame_mem_ctrl, CODA_REG_BIT_FRAME_MEM_CTRL);

1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371
	ctx->display_idx = -1;
	ctx->frm_dis_flg = 0;
	coda_write(dev, 0, CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));

	coda_write(dev, CODA_BIT_DEC_SEQ_INIT_ESCAPE,
			CODA_REG_BIT_BIT_STREAM_PARAM);

	coda_write(dev, bitstream_buf, CODA_CMD_DEC_SEQ_BB_START);
	coda_write(dev, bitstream_size / 1024, CODA_CMD_DEC_SEQ_BB_SIZE);
	val = 0;
	if ((dev->devtype->product == CODA_7541) ||
	    (dev->devtype->product == CODA_960))
		val |= CODA_REORDER_ENABLE;
1372 1373
	if (ctx->codec->src_fourcc == V4L2_PIX_FMT_JPEG)
		val |= CODA_NO_INT_ENABLE;
1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459
	coda_write(dev, val, CODA_CMD_DEC_SEQ_OPTION);

	ctx->params.codec_mode = ctx->codec->mode;
	if (dev->devtype->product == CODA_960 &&
	    src_fourcc == V4L2_PIX_FMT_MPEG4)
		ctx->params.codec_mode_aux = CODA_MP4_AUX_MPEG4;
	else
		ctx->params.codec_mode_aux = 0;
	if (src_fourcc == V4L2_PIX_FMT_H264) {
		if (dev->devtype->product == CODA_7541) {
			coda_write(dev, ctx->psbuf.paddr,
					CODA_CMD_DEC_SEQ_PS_BB_START);
			coda_write(dev, (CODA7_PS_BUF_SIZE / 1024),
					CODA_CMD_DEC_SEQ_PS_BB_SIZE);
		}
		if (dev->devtype->product == CODA_960) {
			coda_write(dev, 0, CODA_CMD_DEC_SEQ_X264_MV_EN);
			coda_write(dev, 512, CODA_CMD_DEC_SEQ_SPP_CHUNK_SIZE);
		}
	}
	if (dev->devtype->product != CODA_960)
		coda_write(dev, 0, CODA_CMD_DEC_SEQ_SRC_SIZE);

	if (coda_command_sync(ctx, CODA_COMMAND_SEQ_INIT)) {
		v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
		coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
		return -ETIMEDOUT;
	}

	/* Update kfifo out pointer from coda bitstream read pointer */
	coda_kfifo_sync_from_device(ctx);

	coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);

	if (coda_read(dev, CODA_RET_DEC_SEQ_SUCCESS) == 0) {
		v4l2_err(&dev->v4l2_dev,
			"CODA_COMMAND_SEQ_INIT failed, error code = %d\n",
			coda_read(dev, CODA_RET_DEC_SEQ_ERR_REASON));
		return -EAGAIN;
	}

	val = coda_read(dev, CODA_RET_DEC_SEQ_SRC_SIZE);
	if (dev->devtype->product == CODA_DX6) {
		width = (val >> CODADX6_PICWIDTH_OFFSET) & CODADX6_PICWIDTH_MASK;
		height = val & CODADX6_PICHEIGHT_MASK;
	} else {
		width = (val >> CODA7_PICWIDTH_OFFSET) & CODA7_PICWIDTH_MASK;
		height = val & CODA7_PICHEIGHT_MASK;
	}

	if (width > q_data_dst->width || height > q_data_dst->height) {
		v4l2_err(&dev->v4l2_dev, "stream is %dx%d, not %dx%d\n",
			 width, height, q_data_dst->width, q_data_dst->height);
		return -EINVAL;
	}

	width = round_up(width, 16);
	height = round_up(height, 16);

	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "%s instance %d now: %dx%d\n",
		 __func__, ctx->idx, width, height);

	ctx->num_internal_frames = coda_read(dev, CODA_RET_DEC_SEQ_FRAME_NEED);
	if (ctx->num_internal_frames > CODA_MAX_FRAMEBUFFERS) {
		v4l2_err(&dev->v4l2_dev,
			 "not enough framebuffers to decode (%d < %d)\n",
			 CODA_MAX_FRAMEBUFFERS, ctx->num_internal_frames);
		return -EINVAL;
	}

	if (src_fourcc == V4L2_PIX_FMT_H264) {
		u32 left_right;
		u32 top_bottom;

		left_right = coda_read(dev, CODA_RET_DEC_SEQ_CROP_LEFT_RIGHT);
		top_bottom = coda_read(dev, CODA_RET_DEC_SEQ_CROP_TOP_BOTTOM);

		q_data_dst->rect.left = (left_right >> 10) & 0x3ff;
		q_data_dst->rect.top = (top_bottom >> 10) & 0x3ff;
		q_data_dst->rect.width = width - q_data_dst->rect.left -
					 (left_right & 0x3ff);
		q_data_dst->rect.height = height - q_data_dst->rect.top -
					  (top_bottom & 0x3ff);
	}

	ret = coda_alloc_framebuffers(ctx, q_data_dst, src_fourcc);
1460 1461
	if (ret < 0) {
		v4l2_err(&dev->v4l2_dev, "failed to allocate framebuffers\n");
1462
		return ret;
1463
	}
1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488

	/* Tell the decoder how many frame buffers we allocated. */
	coda_write(dev, ctx->num_internal_frames, CODA_CMD_SET_FRAME_BUF_NUM);
	coda_write(dev, width, CODA_CMD_SET_FRAME_BUF_STRIDE);

	if (dev->devtype->product != CODA_DX6) {
		/* Set secondary AXI IRAM */
		coda_setup_iram(ctx);

		coda_write(dev, ctx->iram_info.buf_bit_use,
				CODA7_CMD_SET_FRAME_AXI_BIT_ADDR);
		coda_write(dev, ctx->iram_info.buf_ip_ac_dc_use,
				CODA7_CMD_SET_FRAME_AXI_IPACDC_ADDR);
		coda_write(dev, ctx->iram_info.buf_dbk_y_use,
				CODA7_CMD_SET_FRAME_AXI_DBKY_ADDR);
		coda_write(dev, ctx->iram_info.buf_dbk_c_use,
				CODA7_CMD_SET_FRAME_AXI_DBKC_ADDR);
		coda_write(dev, ctx->iram_info.buf_ovl_use,
				CODA7_CMD_SET_FRAME_AXI_OVL_ADDR);
		if (dev->devtype->product == CODA_960)
			coda_write(dev, ctx->iram_info.buf_btp_use,
					CODA9_CMD_SET_FRAME_AXI_BTP_ADDR);
	}

	if (dev->devtype->product == CODA_960) {
1489
		int cbb_size, crb_size;
1490

1491 1492
		coda_write(dev, -1, CODA9_CMD_SET_FRAME_DELAY);
		/* Luma 2x0 page, 2x6 cache, chroma 2x0 page, 2x4 cache size */
1493
		coda_write(dev, 0x20262024, CODA9_CMD_SET_FRAME_CACHE_SIZE);
1494 1495 1496 1497 1498 1499 1500 1501

		if (dst_fourcc == V4L2_PIX_FMT_NV12) {
			cbb_size = 0;
			crb_size = 16;
		} else {
			cbb_size = 8;
			crb_size = 8;
		}
1502 1503
		coda_write(dev, 2 << CODA9_CACHE_PAGEMERGE_OFFSET |
				32 << CODA9_CACHE_LUMA_BUFFER_SIZE_OFFSET |
1504 1505
				cbb_size << CODA9_CACHE_CB_BUFFER_SIZE_OFFSET |
				crb_size << CODA9_CACHE_CR_BUFFER_SIZE_OFFSET,
1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557
				CODA9_CMD_SET_FRAME_CACHE_CONFIG);
	}

	if (src_fourcc == V4L2_PIX_FMT_H264) {
		coda_write(dev, ctx->slicebuf.paddr,
				CODA_CMD_SET_FRAME_SLICE_BB_START);
		coda_write(dev, ctx->slicebuf.size / 1024,
				CODA_CMD_SET_FRAME_SLICE_BB_SIZE);
	}

	if (dev->devtype->product == CODA_7541) {
		int max_mb_x = 1920 / 16;
		int max_mb_y = 1088 / 16;
		int max_mb_num = max_mb_x * max_mb_y;

		coda_write(dev, max_mb_num << 16 | max_mb_x << 8 | max_mb_y,
				CODA7_CMD_SET_FRAME_MAX_DEC_SIZE);
	} else if (dev->devtype->product == CODA_960) {
		int max_mb_x = 1920 / 16;
		int max_mb_y = 1088 / 16;
		int max_mb_num = max_mb_x * max_mb_y;

		coda_write(dev, max_mb_num << 16 | max_mb_x << 8 | max_mb_y,
				CODA9_CMD_SET_FRAME_MAX_DEC_SIZE);
	}

	if (coda_command_sync(ctx, CODA_COMMAND_SET_FRAME_BUF)) {
		v4l2_err(&ctx->dev->v4l2_dev,
			 "CODA_COMMAND_SET_FRAME_BUF timeout\n");
		return -ETIMEDOUT;
	}

	return 0;
}

static int coda_start_decoding(struct coda_ctx *ctx)
{
	struct coda_dev *dev = ctx->dev;
	int ret;

	mutex_lock(&dev->coda_mutex);
	ret = __coda_start_decoding(ctx);
	mutex_unlock(&dev->coda_mutex);

	return ret;
}

static int coda_prepare_decode(struct coda_ctx *ctx)
{
	struct vb2_buffer *dst_buf;
	struct coda_dev *dev = ctx->dev;
	struct coda_q_data *q_data_dst;
1558
	u32 reg_addr, reg_stride;
1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601

	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);

	/* Try to copy source buffer contents into the bitstream ringbuffer */
	mutex_lock(&ctx->bitstream_mutex);
	coda_fill_bitstream(ctx);
	mutex_unlock(&ctx->bitstream_mutex);

	if (coda_get_bitstream_payload(ctx) < 512 &&
	    (!(ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG))) {
		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
			 "bitstream payload: %d, skipping\n",
			 coda_get_bitstream_payload(ctx));
		v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
		return -EAGAIN;
	}

	/* Run coda_start_decoding (again) if not yet initialized */
	if (!ctx->initialized) {
		int ret = __coda_start_decoding(ctx);

		if (ret < 0) {
			v4l2_err(&dev->v4l2_dev, "failed to start decoding\n");
			v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
			return -EAGAIN;
		} else {
			ctx->initialized = 1;
		}
	}

	if (dev->devtype->product == CODA_960)
		coda_set_gdi_regs(ctx);

	if (dev->devtype->product == CODA_960) {
		/*
		 * The CODA960 seems to have an internal list of buffers with
		 * 64 entries that includes the registered frame buffers as
		 * well as the rotator buffer output.
		 * ROT_INDEX needs to be < 0x40, but > ctx->num_internal_frames.
		 */
		coda_write(dev, CODA_MAX_FRAMEBUFFERS + dst_buf->v4l2_buf.index,
				CODA9_CMD_DEC_PIC_ROT_INDEX);
1602 1603 1604

		reg_addr = CODA9_CMD_DEC_PIC_ROT_ADDR_Y;
		reg_stride = CODA9_CMD_DEC_PIC_ROT_STRIDE;
1605
	} else {
1606 1607
		reg_addr = CODA_CMD_DEC_PIC_ROT_ADDR_Y;
		reg_stride = CODA_CMD_DEC_PIC_ROT_STRIDE;
1608
	}
1609 1610 1611
	coda_write_base(ctx, q_data_dst, dst_buf, reg_addr);
	coda_write(dev, q_data_dst->bytesperline, reg_stride);

1612 1613 1614 1615 1616 1617 1618 1619 1620 1621
	coda_write(dev, CODA_ROT_MIR_ENABLE | ctx->params.rot_mode,
			CODA_CMD_DEC_PIC_ROT_MODE);

	switch (dev->devtype->product) {
	case CODA_DX6:
		/* TBD */
	case CODA_7541:
		coda_write(dev, CODA_PRE_SCAN_EN, CODA_CMD_DEC_PIC_OPTION);
		break;
	case CODA_960:
P
Philipp Zabel 已提交
1622 1623
		/* 'hardcode to use interrupt disable mode'? */
		coda_write(dev, (1 << 10), CODA_CMD_DEC_PIC_OPTION);
1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635
		break;
	}

	coda_write(dev, 0, CODA_CMD_DEC_PIC_SKIP_NUM);

	coda_write(dev, 0, CODA_CMD_DEC_PIC_BB_START);
	coda_write(dev, 0, CODA_CMD_DEC_PIC_START_BYTE);

	if (dev->devtype->product != CODA_DX6)
		coda_write(dev, ctx->iram_info.axi_sram_use,
				CODA7_REG_BIT_AXI_SRAM_USE);

1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655
	if (ctx->codec->src_fourcc == V4L2_PIX_FMT_JPEG) {
		struct coda_buffer_meta *meta;

		/* If this is the last buffer in the bitstream, add padding */
		meta = list_first_entry(&ctx->buffer_meta_list,
				      struct coda_buffer_meta, list);
		if (meta->end == (ctx->bitstream_fifo.kfifo.in &
				  ctx->bitstream_fifo.kfifo.mask)) {
			static unsigned char buf[512];
			unsigned int pad;

			/* Pad to multiple of 256 and then add 256 more */
			pad = ((0 - meta->end) & 0xff) + 256;

			memset(buf, 0xff, sizeof(buf));

			kfifo_in(&ctx->bitstream_fifo, buf, pad);
		}
	}

1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668
	coda_kfifo_sync_to_device_full(ctx);

	coda_command_async(ctx, CODA_COMMAND_PIC_RUN);

	return 0;
}

static void coda_finish_decode(struct coda_ctx *ctx)
{
	struct coda_dev *dev = ctx->dev;
	struct coda_q_data *q_data_src;
	struct coda_q_data *q_data_dst;
	struct vb2_buffer *dst_buf;
1669
	struct coda_buffer_meta *meta;
1670
	unsigned long payload;
1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759
	int width, height;
	int decoded_idx;
	int display_idx;
	u32 src_fourcc;
	int success;
	u32 err_mb;
	u32 val;

	/* Update kfifo out pointer from coda bitstream read pointer */
	coda_kfifo_sync_from_device(ctx);

	/*
	 * in stream-end mode, the read pointer can overshoot the write pointer
	 * by up to 512 bytes
	 */
	if (ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG) {
		if (coda_get_bitstream_payload(ctx) >= CODA_MAX_FRAME_SIZE - 512)
			kfifo_init(&ctx->bitstream_fifo,
				ctx->bitstream.vaddr, ctx->bitstream.size);
	}

	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
	src_fourcc = q_data_src->fourcc;

	val = coda_read(dev, CODA_RET_DEC_PIC_SUCCESS);
	if (val != 1)
		pr_err("DEC_PIC_SUCCESS = %d\n", val);

	success = val & 0x1;
	if (!success)
		v4l2_err(&dev->v4l2_dev, "decode failed\n");

	if (src_fourcc == V4L2_PIX_FMT_H264) {
		if (val & (1 << 3))
			v4l2_err(&dev->v4l2_dev,
				 "insufficient PS buffer space (%d bytes)\n",
				 ctx->psbuf.size);
		if (val & (1 << 2))
			v4l2_err(&dev->v4l2_dev,
				 "insufficient slice buffer space (%d bytes)\n",
				 ctx->slicebuf.size);
	}

	val = coda_read(dev, CODA_RET_DEC_PIC_SIZE);
	width = (val >> 16) & 0xffff;
	height = val & 0xffff;

	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);

	/* frame crop information */
	if (src_fourcc == V4L2_PIX_FMT_H264) {
		u32 left_right;
		u32 top_bottom;

		left_right = coda_read(dev, CODA_RET_DEC_PIC_CROP_LEFT_RIGHT);
		top_bottom = coda_read(dev, CODA_RET_DEC_PIC_CROP_TOP_BOTTOM);

		if (left_right == 0xffffffff && top_bottom == 0xffffffff) {
			/* Keep current crop information */
		} else {
			struct v4l2_rect *rect = &q_data_dst->rect;

			rect->left = left_right >> 16 & 0xffff;
			rect->top = top_bottom >> 16 & 0xffff;
			rect->width = width - rect->left -
				      (left_right & 0xffff);
			rect->height = height - rect->top -
				       (top_bottom & 0xffff);
		}
	} else {
		/* no cropping */
	}

	err_mb = coda_read(dev, CODA_RET_DEC_PIC_ERR_MB);
	if (err_mb > 0)
		v4l2_err(&dev->v4l2_dev,
			 "errors in %d macroblocks\n", err_mb);

	if (dev->devtype->product == CODA_7541) {
		val = coda_read(dev, CODA_RET_DEC_PIC_OPTION);
		if (val == 0) {
			/* not enough bitstream data */
			v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
				 "prescan failed: %d\n", val);
			ctx->hold = true;
			return;
		}
	}

P
Philipp Zabel 已提交
1760 1761
	ctx->frm_dis_flg = coda_read(dev,
				     CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788

	/*
	 * The previous display frame was copied out by the rotator,
	 * now it can be overwritten again
	 */
	if (ctx->display_idx >= 0 &&
	    ctx->display_idx < ctx->num_internal_frames) {
		ctx->frm_dis_flg &= ~(1 << ctx->display_idx);
		coda_write(dev, ctx->frm_dis_flg,
				CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
	}

	/*
	 * The index of the last decoded frame, not necessarily in
	 * display order, and the index of the next display frame.
	 * The latter could have been decoded in a previous run.
	 */
	decoded_idx = coda_read(dev, CODA_RET_DEC_PIC_CUR_IDX);
	display_idx = coda_read(dev, CODA_RET_DEC_PIC_FRAME_IDX);

	if (decoded_idx == -1) {
		/* no frame was decoded, but we might have a display frame */
		if (display_idx >= 0 && display_idx < ctx->num_internal_frames)
			ctx->sequence_offset++;
		else if (ctx->display_idx < 0)
			ctx->hold = true;
	} else if (decoded_idx == -2) {
P
Philipp Zabel 已提交
1789
		/* no frame was decoded, we still return remaining buffers */
1790 1791 1792 1793 1794 1795
	} else if (decoded_idx < 0 || decoded_idx >= ctx->num_internal_frames) {
		v4l2_err(&dev->v4l2_dev,
			 "decoded frame index out of range: %d\n", decoded_idx);
	} else {
		val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1;
		val -= ctx->sequence_offset;
1796
		mutex_lock(&ctx->bitstream_mutex);
1797 1798 1799 1800 1801
		if (!list_empty(&ctx->buffer_meta_list)) {
			meta = list_first_entry(&ctx->buffer_meta_list,
					      struct coda_buffer_meta, list);
			list_del(&meta->list);
			if (val != (meta->sequence & 0xffff)) {
1802 1803 1804
				v4l2_err(&dev->v4l2_dev,
					 "sequence number mismatch (%d(%d) != %d)\n",
					 val, ctx->sequence_offset,
1805
					 meta->sequence);
1806
			}
1807 1808
			ctx->frame_metas[decoded_idx] = *meta;
			kfree(meta);
1809 1810
		} else {
			v4l2_err(&dev->v4l2_dev, "empty timestamp list!\n");
1811 1812 1813
			memset(&ctx->frame_metas[decoded_idx], 0,
			       sizeof(struct coda_buffer_meta));
			ctx->frame_metas[decoded_idx].sequence = val;
1814
		}
1815
		mutex_unlock(&ctx->bitstream_mutex);
1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851

		val = coda_read(dev, CODA_RET_DEC_PIC_TYPE) & 0x7;
		if (val == 0)
			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_KEYFRAME;
		else if (val == 1)
			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_PFRAME;
		else
			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_BFRAME;

		ctx->frame_errors[decoded_idx] = err_mb;
	}

	if (display_idx == -1) {
		/*
		 * no more frames to be decoded, but there could still
		 * be rotator output to dequeue
		 */
		ctx->hold = true;
	} else if (display_idx == -3) {
		/* possibly prescan failure */
	} else if (display_idx < 0 || display_idx >= ctx->num_internal_frames) {
		v4l2_err(&dev->v4l2_dev,
			 "presentation frame index out of range: %d\n",
			 display_idx);
	}

	/* If a frame was copied out, return it */
	if (ctx->display_idx >= 0 &&
	    ctx->display_idx < ctx->num_internal_frames) {
		dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
		dst_buf->v4l2_buf.sequence = ctx->osequence++;

		dst_buf->v4l2_buf.flags &= ~(V4L2_BUF_FLAG_KEYFRAME |
					     V4L2_BUF_FLAG_PFRAME |
					     V4L2_BUF_FLAG_BFRAME);
		dst_buf->v4l2_buf.flags |= ctx->frame_types[ctx->display_idx];
1852 1853 1854
		meta = &ctx->frame_metas[ctx->display_idx];
		dst_buf->v4l2_buf.timecode = meta->timecode;
		dst_buf->v4l2_buf.timestamp = meta->timestamp;
1855

1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
		switch (q_data_dst->fourcc) {
		case V4L2_PIX_FMT_YUV420:
		case V4L2_PIX_FMT_YVU420:
		case V4L2_PIX_FMT_NV12:
		default:
			payload = width * height * 3 / 2;
			break;
		case V4L2_PIX_FMT_YUV422P:
			payload = width * height * 2;
			break;
		}
		vb2_set_plane_payload(dst_buf, 0, payload);
1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906

		v4l2_m2m_buf_done(dst_buf, ctx->frame_errors[display_idx] ?
				  VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);

		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
			"job finished: decoding frame (%d) (%s)\n",
			dst_buf->v4l2_buf.sequence,
			(dst_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) ?
			"KEYFRAME" : "PFRAME");
	} else {
		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
			"job finished: no frame decoded\n");
	}

	/* The rotator will copy the current display frame next time */
	ctx->display_idx = display_idx;
}

const struct coda_context_ops coda_bit_decode_ops = {
	.queue_init = coda_decoder_queue_init,
	.start_streaming = coda_start_decoding,
	.prepare_run = coda_prepare_decode,
	.finish_run = coda_finish_decode,
	.seq_end_work = coda_seq_end_work,
	.release = coda_bit_release,
};

irqreturn_t coda_irq_handler(int irq, void *data)
{
	struct coda_dev *dev = data;
	struct coda_ctx *ctx;

	/* read status register to attend the IRQ */
	coda_read(dev, CODA_REG_BIT_INT_STATUS);
	coda_write(dev, CODA_REG_BIT_INT_CLEAR_SET,
		      CODA_REG_BIT_INT_CLEAR);

	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
	if (ctx == NULL) {
P
Philipp Zabel 已提交
1907 1908
		v4l2_err(&dev->v4l2_dev,
			 "Instance released before the end of transaction\n");
1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927
		mutex_unlock(&dev->coda_mutex);
		return IRQ_HANDLED;
	}

	if (ctx->aborting) {
		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
			 "task has been aborted\n");
	}

	if (coda_isbusy(ctx->dev)) {
		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
			 "coda is still busy!!!!\n");
		return IRQ_NONE;
	}

	complete(&ctx->completion);

	return IRQ_HANDLED;
}