shdma.c 23.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
/*
 * Renesas SuperH DMA Engine support
 *
 * base is drivers/dma/flsdma.c
 *
 * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
 * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
 * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
 *
 * This 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.
 *
 * - DMA of SuperH does not have Hardware DMA chain mode.
 * - MAX DMA size is 16MB.
 *
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/dmaengine.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/platform_device.h>
#include <cpu/dma.h>
#include <asm/dma-sh.h>
#include "shdma.h"

/* DMA descriptor control */
32 33 34 35 36 37 38
enum sh_dmae_desc_status {
	DESC_IDLE,
	DESC_PREPARED,
	DESC_SUBMITTED,
	DESC_COMPLETED,	/* completed, have to call callback */
	DESC_WAITING,	/* callback called, waiting for ack / re-submit */
};
39 40 41 42 43 44 45 46 47 48 49 50

#define NR_DESCS_PER_CHANNEL 32
/*
 * Define the default configuration for dual address memory-memory transfer.
 * The 0x400 value represents auto-request, external->external.
 *
 * And this driver set 4byte burst mode.
 * If you want to change mode, you need to change RS_DEFAULT of value.
 * (ex 1byte burst mode -> (RS_DUAL & ~TS_32)
 */
#define RS_DEFAULT  (RS_DUAL)

51 52
static void sh_dmae_chan_ld_cleanup(struct sh_dmae_chan *sh_chan, bool all);

53 54 55
#define SH_DMAC_CHAN_BASE(id) (dma_base_addr[id])
static void sh_dmae_writel(struct sh_dmae_chan *sh_dc, u32 data, u32 reg)
{
56
	ctrl_outl(data, SH_DMAC_CHAN_BASE(sh_dc->id) + reg);
57 58 59 60
}

static u32 sh_dmae_readl(struct sh_dmae_chan *sh_dc, u32 reg)
{
61
	return ctrl_inl(SH_DMAC_CHAN_BASE(sh_dc->id) + reg);
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
}

static void dmae_init(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = RS_DEFAULT; /* default is DUAL mode */
	sh_dmae_writel(sh_chan, chcr, CHCR);
}

/*
 * Reset DMA controller
 *
 * SH7780 has two DMAOR register
 */
static void sh_dmae_ctl_stop(int id)
{
	unsigned short dmaor = dmaor_read_reg(id);

	dmaor &= ~(DMAOR_NMIF | DMAOR_AE);
	dmaor_write_reg(id, dmaor);
}

static int sh_dmae_rst(int id)
{
	unsigned short dmaor;

	sh_dmae_ctl_stop(id);
88
	dmaor = dmaor_read_reg(id) | DMAOR_INIT;
89 90

	dmaor_write_reg(id, dmaor);
91
	if (dmaor_read_reg(id) & (DMAOR_AE | DMAOR_NMIF)) {
92 93 94 95 96 97
		pr_warning(KERN_ERR "dma-sh: Can't initialize DMAOR.\n");
		return -EINVAL;
	}
	return 0;
}

98
static bool dmae_is_busy(struct sh_dmae_chan *sh_chan)
99 100
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
101 102 103 104 105

	if ((chcr & (CHCR_DE | CHCR_TE)) == CHCR_DE)
		return true; /* working */

	return false; /* waiting */
106 107 108 109 110 111 112 113
}

static inline unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
	return ts_shift[(chcr & CHCR_TS_MASK) >> CHCR_TS_SHIFT];
}

114
static void dmae_set_reg(struct sh_dmae_chan *sh_chan, struct sh_dmae_regs *hw)
115
{
116 117 118
	sh_dmae_writel(sh_chan, hw->sar, SAR);
	sh_dmae_writel(sh_chan, hw->dar, DAR);
	sh_dmae_writel(sh_chan, hw->tcr >> calc_xmit_shift(sh_chan), TCR);
119 120 121 122 123 124
}

static void dmae_start(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

125
	chcr |= CHCR_DE | CHCR_IE;
126 127 128 129 130 131 132 133 134 135 136 137 138 139
	sh_dmae_writel(sh_chan, chcr, CHCR);
}

static void dmae_halt(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

	chcr &= ~(CHCR_DE | CHCR_TE | CHCR_IE);
	sh_dmae_writel(sh_chan, chcr, CHCR);
}

static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val)
{
	/* When DMA was working, can not set data to CHCR */
140 141
	if (dmae_is_busy(sh_chan))
		return -EBUSY;
142 143 144 145 146 147 148 149 150 151 152 153 154

	sh_dmae_writel(sh_chan, val, CHCR);
	return 0;
}

#define DMARS1_ADDR	0x04
#define DMARS2_ADDR	0x08
#define DMARS_SHIFT 8
#define DMARS_CHAN_MSK 0x01
static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
{
	u32 addr;
	int shift = 0;
155 156 157

	if (dmae_is_busy(sh_chan))
		return -EBUSY;
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190

	if (sh_chan->id & DMARS_CHAN_MSK)
		shift = DMARS_SHIFT;

	switch (sh_chan->id) {
	/* DMARS0 */
	case 0:
	case 1:
		addr = SH_DMARS_BASE;
		break;
	/* DMARS1 */
	case 2:
	case 3:
		addr = (SH_DMARS_BASE + DMARS1_ADDR);
		break;
	/* DMARS2 */
	case 4:
	case 5:
		addr = (SH_DMARS_BASE + DMARS2_ADDR);
		break;
	default:
		return -EINVAL;
	}

	ctrl_outw((val << shift) |
		(ctrl_inw(addr) & (shift ? 0xFF00 : 0x00FF)),
		addr);

	return 0;
}

static dma_cookie_t sh_dmae_tx_submit(struct dma_async_tx_descriptor *tx)
{
191
	struct sh_desc *desc = tx_to_sh_desc(tx), *chunk, *last = desc, *c;
192
	struct sh_dmae_chan *sh_chan = to_sh_chan(tx->chan);
193
	dma_async_tx_callback callback = tx->callback;
194 195 196 197 198 199 200 201 202
	dma_cookie_t cookie;

	spin_lock_bh(&sh_chan->desc_lock);

	cookie = sh_chan->common.cookie;
	cookie++;
	if (cookie < 0)
		cookie = 1;

203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
	sh_chan->common.cookie = cookie;
	tx->cookie = cookie;

	/* Mark all chunks of this descriptor as submitted, move to the queue */
	list_for_each_entry_safe(chunk, c, desc->node.prev, node) {
		/*
		 * All chunks are on the global ld_free, so, we have to find
		 * the end of the chain ourselves
		 */
		if (chunk != desc && (chunk->mark == DESC_IDLE ||
				      chunk->async_tx.cookie > 0 ||
				      chunk->async_tx.cookie == -EBUSY ||
				      &chunk->node == &sh_chan->ld_free))
			break;
		chunk->mark = DESC_SUBMITTED;
		/* Callback goes to the last chunk */
		chunk->async_tx.callback = NULL;
		chunk->cookie = cookie;
		list_move_tail(&chunk->node, &sh_chan->ld_queue);
		last = chunk;
	}
224

225 226 227 228 229 230
	last->async_tx.callback = callback;
	last->async_tx.callback_param = tx->callback_param;

	dev_dbg(sh_chan->dev, "submit #%d@%p on %d: %x[%d] -> %x\n",
		tx->cookie, &last->async_tx, sh_chan->id,
		desc->hw.sar, desc->hw.tcr, desc->hw.dar);
231 232 233 234 235 236

	spin_unlock_bh(&sh_chan->desc_lock);

	return cookie;
}

237
/* Called with desc_lock held */
238 239
static struct sh_desc *sh_dmae_get_desc(struct sh_dmae_chan *sh_chan)
{
240
	struct sh_desc *desc;
241

242 243 244
	list_for_each_entry(desc, &sh_chan->ld_free, node)
		if (desc->mark != DESC_PREPARED) {
			BUG_ON(desc->mark != DESC_IDLE);
245
			list_del(&desc->node);
246
			return desc;
247 248
		}

249
	return NULL;
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267
}

static int sh_dmae_alloc_chan_resources(struct dma_chan *chan)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	struct sh_desc *desc;

	spin_lock_bh(&sh_chan->desc_lock);
	while (sh_chan->descs_allocated < NR_DESCS_PER_CHANNEL) {
		spin_unlock_bh(&sh_chan->desc_lock);
		desc = kzalloc(sizeof(struct sh_desc), GFP_KERNEL);
		if (!desc) {
			spin_lock_bh(&sh_chan->desc_lock);
			break;
		}
		dma_async_tx_descriptor_init(&desc->async_tx,
					&sh_chan->common);
		desc->async_tx.tx_submit = sh_dmae_tx_submit;
268
		desc->mark = DESC_IDLE;
269 270

		spin_lock_bh(&sh_chan->desc_lock);
271
		list_add(&desc->node, &sh_chan->ld_free);
272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
		sh_chan->descs_allocated++;
	}
	spin_unlock_bh(&sh_chan->desc_lock);

	return sh_chan->descs_allocated;
}

/*
 * sh_dma_free_chan_resources - Free all resources of the channel.
 */
static void sh_dmae_free_chan_resources(struct dma_chan *chan)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	struct sh_desc *desc, *_desc;
	LIST_HEAD(list);

288 289 290 291
	/* Prepared and not submitted descriptors can still be on the queue */
	if (!list_empty(&sh_chan->ld_queue))
		sh_dmae_chan_ld_cleanup(sh_chan, true);

292 293 294 295 296 297 298 299 300 301 302
	spin_lock_bh(&sh_chan->desc_lock);

	list_splice_init(&sh_chan->ld_free, &list);
	sh_chan->descs_allocated = 0;

	spin_unlock_bh(&sh_chan->desc_lock);

	list_for_each_entry_safe(desc, _desc, &list, node)
		kfree(desc);
}

303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
/*
 * sh_dmae_add_desc - get, set up and return one transfer descriptor
 * @sh_chan:	DMA channel
 * @flags:	DMA transfer flags
 * @dest:	destination DMA address, incremented when direction equals
 *		DMA_FROM_DEVICE or DMA_BIDIRECTIONAL
 * @src:	source DMA address, incremented when direction equals
 *		DMA_TO_DEVICE or DMA_BIDIRECTIONAL
 * @len:	DMA transfer length
 * @first:	if NULL, set to the current descriptor and cookie set to -EBUSY
 * @direction:	needed for slave DMA to decide which address to keep constant,
 *		equals DMA_BIDIRECTIONAL for MEMCPY
 * Returns 0 or an error
 * Locks: called with desc_lock held
 */
static struct sh_desc *sh_dmae_add_desc(struct sh_dmae_chan *sh_chan,
	unsigned long flags, dma_addr_t *dest, dma_addr_t *src, size_t *len,
	struct sh_desc **first, enum dma_data_direction direction)
321
{
322
	struct sh_desc *new;
323 324
	size_t copy_size;

325
	if (!*len)
326 327
		return NULL;

328 329 330 331
	/* Allocate the link descriptor from the free list */
	new = sh_dmae_get_desc(sh_chan);
	if (!new) {
		dev_err(sh_chan->dev, "No free link descriptor available\n");
332
		return NULL;
333
	}
334

335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391
	copy_size = min(*len, (size_t)SH_DMA_TCR_MAX + 1);

	new->hw.sar = *src;
	new->hw.dar = *dest;
	new->hw.tcr = copy_size;

	if (!*first) {
		/* First desc */
		new->async_tx.cookie = -EBUSY;
		*first = new;
	} else {
		/* Other desc - invisible to the user */
		new->async_tx.cookie = -EINVAL;
	}

	dev_dbg(sh_chan->dev, "chaining (%u/%u)@%x -> %x with %p, cookie %d\n",
		copy_size, *len, *src, *dest, &new->async_tx,
		new->async_tx.cookie);

	new->mark = DESC_PREPARED;
	new->async_tx.flags = flags;

	*len -= copy_size;
	if (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE)
		*src += copy_size;
	if (direction == DMA_BIDIRECTIONAL || direction == DMA_FROM_DEVICE)
		*dest += copy_size;

	return new;
}

/*
 * sh_dmae_prep_sg - prepare transfer descriptors from an SG list
 *
 * Common routine for public (MEMCPY) and slave DMA. The MEMCPY case is also
 * converted to scatter-gather to guarantee consistent locking and a correct
 * list manipulation. For slave DMA direction carries the usual meaning, and,
 * logically, the SG list is RAM and the addr variable contains slave address,
 * e.g., the FIFO I/O register. For MEMCPY direction equals DMA_BIDIRECTIONAL
 * and the SG list contains only one element and points at the source buffer.
 */
static struct dma_async_tx_descriptor *sh_dmae_prep_sg(struct sh_dmae_chan *sh_chan,
	struct scatterlist *sgl, unsigned int sg_len, dma_addr_t *addr,
	enum dma_data_direction direction, unsigned long flags)
{
	struct scatterlist *sg;
	struct sh_desc *first = NULL, *new = NULL /* compiler... */;
	LIST_HEAD(tx_list);
	int chunks = 0;
	int i;

	if (!sg_len)
		return NULL;

	for_each_sg(sgl, sg, sg_len, i)
		chunks += (sg_dma_len(sg) + SH_DMA_TCR_MAX) /
			(SH_DMA_TCR_MAX + 1);
392

393 394 395 396 397 398 399 400 401 402 403 404 405 406
	/* Have to lock the whole loop to protect against concurrent release */
	spin_lock_bh(&sh_chan->desc_lock);

	/*
	 * Chaining:
	 * first descriptor is what user is dealing with in all API calls, its
	 *	cookie is at first set to -EBUSY, at tx-submit to a positive
	 *	number
	 * if more than one chunk is needed further chunks have cookie = -EINVAL
	 * the last chunk, if not equal to the first, has cookie = -ENOSPC
	 * all chunks are linked onto the tx_list head with their .node heads
	 *	only during this function, then they are immediately spliced
	 *	back onto the free list in form of a chain
	 */
407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
	for_each_sg(sgl, sg, sg_len, i) {
		dma_addr_t sg_addr = sg_dma_address(sg);
		size_t len = sg_dma_len(sg);

		if (!len)
			goto err_get_desc;

		do {
			dev_dbg(sh_chan->dev, "Add SG #%d@%p[%d], dma %llx\n",
				i, sg, len, (unsigned long long)sg_addr);

			if (direction == DMA_FROM_DEVICE)
				new = sh_dmae_add_desc(sh_chan, flags,
						&sg_addr, addr, &len, &first,
						direction);
			else
				new = sh_dmae_add_desc(sh_chan, flags,
						addr, &sg_addr, &len, &first,
						direction);
			if (!new)
				goto err_get_desc;

			new->chunks = chunks--;
			list_add_tail(&new->node, &tx_list);
		} while (len);
	}
433

434 435
	if (new != first)
		new->async_tx.cookie = -ENOSPC;
436

437 438
	/* Put them back on the free list, so, they don't get lost */
	list_splice_tail(&tx_list, &sh_chan->ld_free);
439

440
	spin_unlock_bh(&sh_chan->desc_lock);
441

442
	return &first->async_tx;
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

err_get_desc:
	list_for_each_entry(new, &tx_list, node)
		new->mark = DESC_IDLE;
	list_splice(&tx_list, &sh_chan->ld_free);

	spin_unlock_bh(&sh_chan->desc_lock);

	return NULL;
}

static struct dma_async_tx_descriptor *sh_dmae_prep_memcpy(
	struct dma_chan *chan, dma_addr_t dma_dest, dma_addr_t dma_src,
	size_t len, unsigned long flags)
{
	struct sh_dmae_chan *sh_chan;
	struct scatterlist sg;

	if (!chan || !len)
		return NULL;

	sh_chan = to_sh_chan(chan);

	sg_init_table(&sg, 1);
	sg_set_page(&sg, pfn_to_page(PFN_DOWN(dma_src)), len,
		    offset_in_page(dma_src));
	sg_dma_address(&sg) = dma_src;
	sg_dma_len(&sg) = len;

	return sh_dmae_prep_sg(sh_chan, &sg, 1, &dma_dest, DMA_BIDIRECTIONAL,
			       flags);
474 475
}

476
static dma_async_tx_callback __ld_cleanup(struct sh_dmae_chan *sh_chan, bool all)
477 478
{
	struct sh_desc *desc, *_desc;
479 480 481 482 483
	/* Is the "exposed" head of a chain acked? */
	bool head_acked = false;
	dma_cookie_t cookie = 0;
	dma_async_tx_callback callback = NULL;
	void *param = NULL;
484 485 486

	spin_lock_bh(&sh_chan->desc_lock);
	list_for_each_entry_safe(desc, _desc, &sh_chan->ld_queue, node) {
487 488 489 490 491 492 493 494 495 496 497 498 499 500
		struct dma_async_tx_descriptor *tx = &desc->async_tx;

		BUG_ON(tx->cookie > 0 && tx->cookie != desc->cookie);
		BUG_ON(desc->mark != DESC_SUBMITTED &&
		       desc->mark != DESC_COMPLETED &&
		       desc->mark != DESC_WAITING);

		/*
		 * queue is ordered, and we use this loop to (1) clean up all
		 * completed descriptors, and to (2) update descriptor flags of
		 * any chunks in a (partially) completed chain
		 */
		if (!all && desc->mark == DESC_SUBMITTED &&
		    desc->cookie != cookie)
501 502
			break;

503 504
		if (tx->cookie > 0)
			cookie = tx->cookie;
505

506 507 508 509
		if (desc->mark == DESC_COMPLETED && desc->chunks == 1) {
			BUG_ON(sh_chan->completed_cookie != desc->cookie - 1);
			sh_chan->completed_cookie = desc->cookie;
		}
510

511 512 513 514 515 516 517 518 519 520
		/* Call callback on the last chunk */
		if (desc->mark == DESC_COMPLETED && tx->callback) {
			desc->mark = DESC_WAITING;
			callback = tx->callback;
			param = tx->callback_param;
			dev_dbg(sh_chan->dev, "descriptor #%d@%p on %d callback\n",
				tx->cookie, tx, sh_chan->id);
			BUG_ON(desc->chunks != 1);
			break;
		}
521

522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547
		if (tx->cookie > 0 || tx->cookie == -EBUSY) {
			if (desc->mark == DESC_COMPLETED) {
				BUG_ON(tx->cookie < 0);
				desc->mark = DESC_WAITING;
			}
			head_acked = async_tx_test_ack(tx);
		} else {
			switch (desc->mark) {
			case DESC_COMPLETED:
				desc->mark = DESC_WAITING;
				/* Fall through */
			case DESC_WAITING:
				if (head_acked)
					async_tx_ack(&desc->async_tx);
			}
		}

		dev_dbg(sh_chan->dev, "descriptor %p #%d completed.\n",
			tx, tx->cookie);

		if (((desc->mark == DESC_COMPLETED ||
		      desc->mark == DESC_WAITING) &&
		     async_tx_test_ack(&desc->async_tx)) || all) {
			/* Remove from ld_queue list */
			desc->mark = DESC_IDLE;
			list_move(&desc->node, &sh_chan->ld_free);
548 549 550
		}
	}
	spin_unlock_bh(&sh_chan->desc_lock);
551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566

	if (callback)
		callback(param);

	return callback;
}

/*
 * sh_chan_ld_cleanup - Clean up link descriptors
 *
 * This function cleans up the ld_queue of DMA channel.
 */
static void sh_dmae_chan_ld_cleanup(struct sh_dmae_chan *sh_chan, bool all)
{
	while (__ld_cleanup(sh_chan, all))
		;
567 568 569 570
}

static void sh_chan_xfer_ld_queue(struct sh_dmae_chan *sh_chan)
{
571
	struct sh_desc *sd;
572

573
	spin_lock_bh(&sh_chan->desc_lock);
574
	/* DMA work check */
575 576
	if (dmae_is_busy(sh_chan)) {
		spin_unlock_bh(&sh_chan->desc_lock);
577
		return;
578
	}
579 580

	/* Find the first un-transfer desciptor */
581 582 583 584 585 586 587 588 589
	list_for_each_entry(sd, &sh_chan->ld_queue, node)
		if (sd->mark == DESC_SUBMITTED) {
			/* Get the ld start address from ld_queue */
			dmae_set_reg(sh_chan, &sd->hw);
			dmae_start(sh_chan);
			break;
		}

	spin_unlock_bh(&sh_chan->desc_lock);
590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606
}

static void sh_dmae_memcpy_issue_pending(struct dma_chan *chan)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	sh_chan_xfer_ld_queue(sh_chan);
}

static enum dma_status sh_dmae_is_complete(struct dma_chan *chan,
					dma_cookie_t cookie,
					dma_cookie_t *done,
					dma_cookie_t *used)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	dma_cookie_t last_used;
	dma_cookie_t last_complete;

607
	sh_dmae_chan_ld_cleanup(sh_chan, false);
608 609 610

	last_used = chan->cookie;
	last_complete = sh_chan->completed_cookie;
611
	BUG_ON(last_complete < 0);
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

	if (done)
		*done = last_complete;

	if (used)
		*used = last_used;

	return dma_async_is_complete(cookie, last_complete, last_used);
}

static irqreturn_t sh_dmae_interrupt(int irq, void *data)
{
	irqreturn_t ret = IRQ_NONE;
	struct sh_dmae_chan *sh_chan = (struct sh_dmae_chan *)data;
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

	if (chcr & CHCR_TE) {
		/* DMA stop */
		dmae_halt(sh_chan);

		ret = IRQ_HANDLED;
		tasklet_schedule(&sh_chan->tasklet);
	}

	return ret;
}

#if defined(CONFIG_CPU_SH4)
static irqreturn_t sh_dmae_err(int irq, void *data)
{
	int err = 0;
	struct sh_dmae_device *shdev = (struct sh_dmae_device *)data;

	/* IRQ Multi */
	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
647
		int __maybe_unused cnt = 0;
648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665
		switch (irq) {
#if defined(DMTE6_IRQ) && defined(DMAE1_IRQ)
		case DMTE6_IRQ:
			cnt++;
#endif
		case DMTE0_IRQ:
			if (dmaor_read_reg(cnt) & (DMAOR_NMIF | DMAOR_AE)) {
				disable_irq(irq);
				return IRQ_HANDLED;
			}
		default:
			return IRQ_NONE;
		}
	} else {
		/* reset dma controller */
		err = sh_dmae_rst(0);
		if (err)
			return err;
666
#ifdef SH_DMAC_BASE1
667 668 669 670 671
		if (shdev->pdata.mode & SHDMA_DMAOR1) {
			err = sh_dmae_rst(1);
			if (err)
				return err;
		}
672
#endif
673 674 675 676 677 678 679 680 681
		disable_irq(irq);
		return IRQ_HANDLED;
	}
}
#endif

static void dmae_do_tasklet(unsigned long data)
{
	struct sh_dmae_chan *sh_chan = (struct sh_dmae_chan *)data;
682
	struct sh_desc *desc;
683
	u32 sar_buf = sh_dmae_readl(sh_chan, SAR);
684

685 686 687 688 689 690 691 692
	spin_lock(&sh_chan->desc_lock);
	list_for_each_entry(desc, &sh_chan->ld_queue, node) {
		if ((desc->hw.sar + desc->hw.tcr) == sar_buf &&
		    desc->mark == DESC_SUBMITTED) {
			dev_dbg(sh_chan->dev, "done #%d@%p dst %u\n",
				desc->async_tx.cookie, &desc->async_tx,
				desc->hw.dar);
			desc->mark = DESC_COMPLETED;
693 694 695
			break;
		}
	}
696
	spin_unlock(&sh_chan->desc_lock);
697 698 699

	/* Next desc */
	sh_chan_xfer_ld_queue(sh_chan);
700
	sh_dmae_chan_ld_cleanup(sh_chan, false);
701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720
}

static unsigned int get_dmae_irq(unsigned int id)
{
	unsigned int irq = 0;
	if (id < ARRAY_SIZE(dmte_irq_map))
		irq = dmte_irq_map[id];
	return irq;
}

static int __devinit sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id)
{
	int err;
	unsigned int irq = get_dmae_irq(id);
	unsigned long irqflags = IRQF_DISABLED;
	struct sh_dmae_chan *new_sh_chan;

	/* alloc channel */
	new_sh_chan = kzalloc(sizeof(struct sh_dmae_chan), GFP_KERNEL);
	if (!new_sh_chan) {
721 722
		dev_err(shdev->common.dev,
			"No free memory for allocating dma channels!\n");
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
		return -ENOMEM;
	}

	new_sh_chan->dev = shdev->common.dev;
	new_sh_chan->id = id;

	/* Init DMA tasklet */
	tasklet_init(&new_sh_chan->tasklet, dmae_do_tasklet,
			(unsigned long)new_sh_chan);

	/* Init the channel */
	dmae_init(new_sh_chan);

	spin_lock_init(&new_sh_chan->desc_lock);

	/* Init descripter manage list */
	INIT_LIST_HEAD(&new_sh_chan->ld_queue);
	INIT_LIST_HEAD(&new_sh_chan->ld_free);

	/* copy struct dma_device */
	new_sh_chan->common.device = &shdev->common;

	/* Add the channel to DMA device channel list */
	list_add_tail(&new_sh_chan->common.device_node,
			&shdev->common.channels);
	shdev->common.chancnt++;

	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
		irqflags = IRQF_SHARED;
#if defined(DMTE6_IRQ)
		if (irq >= DMTE6_IRQ)
			irq = DMTE6_IRQ;
		else
#endif
			irq = DMTE0_IRQ;
	}

	snprintf(new_sh_chan->dev_id, sizeof(new_sh_chan->dev_id),
			"sh-dmae%d", new_sh_chan->id);

	/* set up channel irq */
764 765
	err = request_irq(irq, &sh_dmae_interrupt, irqflags,
			  new_sh_chan->dev_id, new_sh_chan);
766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
	if (err) {
		dev_err(shdev->common.dev, "DMA channel %d request_irq error "
			"with return %d\n", id, err);
		goto err_no_irq;
	}

	/* CHCR register control function */
	new_sh_chan->set_chcr = dmae_set_chcr;
	/* DMARS register control function */
	new_sh_chan->set_dmars = dmae_set_dmars;

	shdev->chan[id] = new_sh_chan;
	return 0;

err_no_irq:
	/* remove from dmaengine device node */
	list_del(&new_sh_chan->common.device_node);
	kfree(new_sh_chan);
	return err;
}

static void sh_dmae_chan_remove(struct sh_dmae_device *shdev)
{
	int i;

	for (i = shdev->common.chancnt - 1 ; i >= 0 ; i--) {
		if (shdev->chan[i]) {
			struct sh_dmae_chan *shchan = shdev->chan[i];
			if (!(shdev->pdata.mode & SHDMA_MIX_IRQ))
				free_irq(dmte_irq_map[i], shchan);

			list_del(&shchan->common.device_node);
			kfree(shchan);
			shdev->chan[i] = NULL;
		}
	}
	shdev->common.chancnt = 0;
}

static int __init sh_dmae_probe(struct platform_device *pdev)
{
	int err = 0, cnt, ecnt;
	unsigned long irqflags = IRQF_DISABLED;
#if defined(CONFIG_CPU_SH4)
	int eirq[] = { DMAE0_IRQ,
#if defined(DMAE1_IRQ)
			DMAE1_IRQ
#endif
		};
#endif
	struct sh_dmae_device *shdev;

818 819 820 821
	/* get platform data */
	if (!pdev->dev.platform_data)
		return -ENODEV;

822 823 824
	shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL);
	if (!shdev) {
		dev_err(&pdev->dev, "No enough memory\n");
825
		return -ENOMEM;
826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853
	}

	/* platform data */
	memcpy(&shdev->pdata, pdev->dev.platform_data,
			sizeof(struct sh_dmae_pdata));

	/* reset dma controller */
	err = sh_dmae_rst(0);
	if (err)
		goto rst_err;

	/* SH7780/85/23 has DMAOR1 */
	if (shdev->pdata.mode & SHDMA_DMAOR1) {
		err = sh_dmae_rst(1);
		if (err)
			goto rst_err;
	}

	INIT_LIST_HEAD(&shdev->common.channels);

	dma_cap_set(DMA_MEMCPY, shdev->common.cap_mask);
	shdev->common.device_alloc_chan_resources
		= sh_dmae_alloc_chan_resources;
	shdev->common.device_free_chan_resources = sh_dmae_free_chan_resources;
	shdev->common.device_prep_dma_memcpy = sh_dmae_prep_memcpy;
	shdev->common.device_is_tx_complete = sh_dmae_is_complete;
	shdev->common.device_issue_pending = sh_dmae_memcpy_issue_pending;
	shdev->common.dev = &pdev->dev;
854 855
	/* Default transfer size of 32 bytes requires 32-byte alignment */
	shdev->common.copy_align = 5;
856 857 858 859 860 861 862 863 864 865 866 867

#if defined(CONFIG_CPU_SH4)
	/* Non Mix IRQ mode SH7722/SH7730 etc... */
	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
		irqflags = IRQF_SHARED;
		eirq[0] = DMTE0_IRQ;
#if defined(DMTE6_IRQ) && defined(DMAE1_IRQ)
		eirq[1] = DMTE6_IRQ;
#endif
	}

	for (ecnt = 0 ; ecnt < ARRAY_SIZE(eirq); ecnt++) {
868 869
		err = request_irq(eirq[ecnt], sh_dmae_err, irqflags,
				  "DMAC Address Error", shdev);
870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
		if (err) {
			dev_err(&pdev->dev, "DMA device request_irq"
				"error (irq %d) with return %d\n",
				eirq[ecnt], err);
			goto eirq_err;
		}
	}
#endif /* CONFIG_CPU_SH4 */

	/* Create DMA Channel */
	for (cnt = 0 ; cnt < MAX_DMA_CHANNELS ; cnt++) {
		err = sh_dmae_chan_probe(shdev, cnt);
		if (err)
			goto chan_probe_err;
	}

	platform_set_drvdata(pdev, shdev);
	dma_async_device_register(&shdev->common);

	return err;

chan_probe_err:
	sh_dmae_chan_remove(shdev);

eirq_err:
	for (ecnt-- ; ecnt >= 0; ecnt--)
		free_irq(eirq[ecnt], shdev);

rst_err:
	kfree(shdev);

	return err;
}

static int __exit sh_dmae_remove(struct platform_device *pdev)
{
	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);

	dma_async_device_unregister(&shdev->common);

	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
		free_irq(DMTE0_IRQ, shdev);
#if defined(DMTE6_IRQ)
		free_irq(DMTE6_IRQ, shdev);
#endif
	}

	/* channel data remove */
	sh_dmae_chan_remove(shdev);

	if (!(shdev->pdata.mode & SHDMA_MIX_IRQ)) {
		free_irq(DMAE0_IRQ, shdev);
#if defined(DMAE1_IRQ)
		free_irq(DMAE1_IRQ, shdev);
#endif
	}
	kfree(shdev);

	return 0;
}

static void sh_dmae_shutdown(struct platform_device *pdev)
{
	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
	sh_dmae_ctl_stop(0);
	if (shdev->pdata.mode & SHDMA_DMAOR1)
		sh_dmae_ctl_stop(1);
}

static struct platform_driver sh_dmae_driver = {
	.remove		= __exit_p(sh_dmae_remove),
	.shutdown	= sh_dmae_shutdown,
	.driver = {
		.name	= "sh-dma-engine",
	},
};

static int __init sh_dmae_init(void)
{
	return platform_driver_probe(&sh_dmae_driver, sh_dmae_probe);
}
module_init(sh_dmae_init);

static void __exit sh_dmae_exit(void)
{
	platform_driver_unregister(&sh_dmae_driver);
}
module_exit(sh_dmae_exit);

MODULE_AUTHOR("Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>");
MODULE_DESCRIPTION("Renesas SH DMA Engine driver");
MODULE_LICENSE("GPL");