omap_dmm_tiler.c 20.5 KB
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 32 33 34 35 36 37 38 39 40 41 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830
/*
 * DMM IOMMU driver support functions for TI OMAP processors.
 *
 * Author: Rob Clark <rob@ti.com>
 *         Andy Gross <andy.gross@ti.com>
 *
 * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
 *
 * 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 version 2.
 *
 * This program is distributed "as is" WITHOUT ANY WARRANTY of any
 * kind, whether express or implied; without even the implied warranty
 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 */
#include <linux/init.h>
#include <linux/module.h>
#include <linux/platform_device.h> /* platform_device() */
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/interrupt.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/time.h>
#include <linux/list.h>
#include <linux/semaphore.h>

#include "omap_dmm_tiler.h"
#include "omap_dmm_priv.h"

/* mappings for associating views to luts */
static struct tcm *containers[TILFMT_NFORMATS];
static struct dmm *omap_dmm;

/* Geometry table */
#define GEOM(xshift, yshift, bytes_per_pixel) { \
		.x_shft = (xshift), \
		.y_shft = (yshift), \
		.cpp    = (bytes_per_pixel), \
		.slot_w = 1 << (SLOT_WIDTH_BITS - (xshift)), \
		.slot_h = 1 << (SLOT_HEIGHT_BITS - (yshift)), \
	}

static const struct {
	uint32_t x_shft;	/* unused X-bits (as part of bpp) */
	uint32_t y_shft;	/* unused Y-bits (as part of bpp) */
	uint32_t cpp;		/* bytes/chars per pixel */
	uint32_t slot_w;	/* width of each slot (in pixels) */
	uint32_t slot_h;	/* height of each slot (in pixels) */
} geom[TILFMT_NFORMATS] = {
		[TILFMT_8BIT]  = GEOM(0, 0, 1),
		[TILFMT_16BIT] = GEOM(0, 1, 2),
		[TILFMT_32BIT] = GEOM(1, 1, 4),
		[TILFMT_PAGE]  = GEOM(SLOT_WIDTH_BITS, SLOT_HEIGHT_BITS, 1),
};


/* lookup table for registers w/ per-engine instances */
static const uint32_t reg[][4] = {
		[PAT_STATUS] = {DMM_PAT_STATUS__0, DMM_PAT_STATUS__1,
				DMM_PAT_STATUS__2, DMM_PAT_STATUS__3},
		[PAT_DESCR]  = {DMM_PAT_DESCR__0, DMM_PAT_DESCR__1,
				DMM_PAT_DESCR__2, DMM_PAT_DESCR__3},
};

/* simple allocator to grab next 16 byte aligned memory from txn */
static void *alloc_dma(struct dmm_txn *txn, size_t sz, dma_addr_t *pa)
{
	void *ptr;
	struct refill_engine *engine = txn->engine_handle;

	/* dmm programming requires 16 byte aligned addresses */
	txn->current_pa = round_up(txn->current_pa, 16);
	txn->current_va = (void *)round_up((long)txn->current_va, 16);

	ptr = txn->current_va;
	*pa = txn->current_pa;

	txn->current_pa += sz;
	txn->current_va += sz;

	BUG_ON((txn->current_va - engine->refill_va) > REFILL_BUFFER_SIZE);

	return ptr;
}

/* check status and spin until wait_mask comes true */
static int wait_status(struct refill_engine *engine, uint32_t wait_mask)
{
	struct dmm *dmm = engine->dmm;
	uint32_t r = 0, err, i;

	i = DMM_FIXED_RETRY_COUNT;
	while (true) {
		r = readl(dmm->base + reg[PAT_STATUS][engine->id]);
		err = r & DMM_PATSTATUS_ERR;
		if (err)
			return -EFAULT;

		if ((r & wait_mask) == wait_mask)
			break;

		if (--i == 0)
			return -ETIMEDOUT;

		udelay(1);
	}

	return 0;
}

irqreturn_t omap_dmm_irq_handler(int irq, void *arg)
{
	struct dmm *dmm = arg;
	uint32_t status = readl(dmm->base + DMM_PAT_IRQSTATUS);
	int i;

	/* ack IRQ */
	writel(status, dmm->base + DMM_PAT_IRQSTATUS);

	for (i = 0; i < dmm->num_engines; i++) {
		if (status & DMM_IRQSTAT_LST)
			wake_up_interruptible(&dmm->engines[i].wait_for_refill);

		status >>= 8;
	}

	return IRQ_HANDLED;
}

/**
 * Get a handle for a DMM transaction
 */
static struct dmm_txn *dmm_txn_init(struct dmm *dmm, struct tcm *tcm)
{
	struct dmm_txn *txn = NULL;
	struct refill_engine *engine = NULL;

	down(&dmm->engine_sem);

	/* grab an idle engine */
	spin_lock(&dmm->list_lock);
	if (!list_empty(&dmm->idle_head)) {
		engine = list_entry(dmm->idle_head.next, struct refill_engine,
					idle_node);
		list_del(&engine->idle_node);
	}
	spin_unlock(&dmm->list_lock);

	BUG_ON(!engine);

	txn = &engine->txn;
	engine->tcm = tcm;
	txn->engine_handle = engine;
	txn->last_pat = NULL;
	txn->current_va = engine->refill_va;
	txn->current_pa = engine->refill_pa;

	return txn;
}

/**
 * Add region to DMM transaction.  If pages or pages[i] is NULL, then the
 * corresponding slot is cleared (ie. dummy_pa is programmed)
 */
static int dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
		struct page **pages, uint32_t npages, uint32_t roll)
{
	dma_addr_t pat_pa = 0;
	uint32_t *data;
	struct pat *pat;
	struct refill_engine *engine = txn->engine_handle;
	int columns = (1 + area->x1 - area->x0);
	int rows = (1 + area->y1 - area->y0);
	int i = columns*rows;
	u32 *lut = omap_dmm->lut + (engine->tcm->lut_id * omap_dmm->lut_width *
			omap_dmm->lut_height) +
			(area->y0 * omap_dmm->lut_width) + area->x0;

	pat = alloc_dma(txn, sizeof(struct pat), &pat_pa);

	if (txn->last_pat)
		txn->last_pat->next_pa = (uint32_t)pat_pa;

	pat->area = *area;
	pat->ctrl = (struct pat_ctrl){
			.start = 1,
			.lut_id = engine->tcm->lut_id,
		};

	data = alloc_dma(txn, 4*i, &pat->data_pa);

	while (i--) {
		int n = i + roll;
		if (n >= npages)
			n -= npages;
		data[i] = (pages && pages[n]) ?
			page_to_phys(pages[n]) : engine->dmm->dummy_pa;
	}

	/* fill in lut with new addresses */
	for (i = 0; i < rows; i++, lut += omap_dmm->lut_width)
		memcpy(lut, &data[i*columns], columns * sizeof(u32));

	txn->last_pat = pat;

	return 0;
}

/**
 * Commit the DMM transaction.
 */
static int dmm_txn_commit(struct dmm_txn *txn, bool wait)
{
	int ret = 0;
	struct refill_engine *engine = txn->engine_handle;
	struct dmm *dmm = engine->dmm;

	if (!txn->last_pat) {
		dev_err(engine->dmm->dev, "need at least one txn\n");
		ret = -EINVAL;
		goto cleanup;
	}

	txn->last_pat->next_pa = 0;

	/* write to PAT_DESCR to clear out any pending transaction */
	writel(0x0, dmm->base + reg[PAT_DESCR][engine->id]);

	/* wait for engine ready: */
	ret = wait_status(engine, DMM_PATSTATUS_READY);
	if (ret) {
		ret = -EFAULT;
		goto cleanup;
	}

	/* kick reload */
	writel(engine->refill_pa,
		dmm->base + reg[PAT_DESCR][engine->id]);

	if (wait) {
		if (wait_event_interruptible_timeout(engine->wait_for_refill,
				wait_status(engine, DMM_PATSTATUS_READY) == 0,
				msecs_to_jiffies(1)) <= 0) {
			dev_err(dmm->dev, "timed out waiting for done\n");
			ret = -ETIMEDOUT;
		}
	}

cleanup:
	spin_lock(&dmm->list_lock);
	list_add(&engine->idle_node, &dmm->idle_head);
	spin_unlock(&dmm->list_lock);

	up(&omap_dmm->engine_sem);
	return ret;
}

/*
 * DMM programming
 */
static int fill(struct tcm_area *area, struct page **pages,
		uint32_t npages, uint32_t roll, bool wait)
{
	int ret = 0;
	struct tcm_area slice, area_s;
	struct dmm_txn *txn;

	txn = dmm_txn_init(omap_dmm, area->tcm);
	if (IS_ERR_OR_NULL(txn))
		return PTR_ERR(txn);

	tcm_for_each_slice(slice, *area, area_s) {
		struct pat_area p_area = {
				.x0 = slice.p0.x,  .y0 = slice.p0.y,
				.x1 = slice.p1.x,  .y1 = slice.p1.y,
		};

		ret = dmm_txn_append(txn, &p_area, pages, npages, roll);
		if (ret)
			goto fail;

		roll += tcm_sizeof(slice);
	}

	ret = dmm_txn_commit(txn, wait);

fail:
	return ret;
}

/*
 * Pin/unpin
 */

/* note: slots for which pages[i] == NULL are filled w/ dummy page
 */
int tiler_pin(struct tiler_block *block, struct page **pages,
		uint32_t npages, uint32_t roll, bool wait)
{
	int ret;

	ret = fill(&block->area, pages, npages, roll, wait);

	if (ret)
		tiler_unpin(block);

	return ret;
}

int tiler_unpin(struct tiler_block *block)
{
	return fill(&block->area, NULL, 0, 0, false);
}

/*
 * Reserve/release
 */
struct tiler_block *tiler_reserve_2d(enum tiler_fmt fmt, uint16_t w,
		uint16_t h, uint16_t align)
{
	struct tiler_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
	u32 min_align = 128;
	int ret;

	BUG_ON(!validfmt(fmt));

	/* convert width/height to slots */
	w = DIV_ROUND_UP(w, geom[fmt].slot_w);
	h = DIV_ROUND_UP(h, geom[fmt].slot_h);

	/* convert alignment to slots */
	min_align = max(min_align, (geom[fmt].slot_w * geom[fmt].cpp));
	align = ALIGN(align, min_align);
	align /= geom[fmt].slot_w * geom[fmt].cpp;

	block->fmt = fmt;

	ret = tcm_reserve_2d(containers[fmt], w, h, align, &block->area);
	if (ret) {
		kfree(block);
		return 0;
	}

	/* add to allocation list */
	spin_lock(&omap_dmm->list_lock);
	list_add(&block->alloc_node, &omap_dmm->alloc_head);
	spin_unlock(&omap_dmm->list_lock);

	return block;
}

struct tiler_block *tiler_reserve_1d(size_t size)
{
	struct tiler_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
	int num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;

	if (!block)
		return 0;

	block->fmt = TILFMT_PAGE;

	if (tcm_reserve_1d(containers[TILFMT_PAGE], num_pages,
				&block->area)) {
		kfree(block);
		return 0;
	}

	spin_lock(&omap_dmm->list_lock);
	list_add(&block->alloc_node, &omap_dmm->alloc_head);
	spin_unlock(&omap_dmm->list_lock);

	return block;
}

/* note: if you have pin'd pages, you should have already unpin'd first! */
int tiler_release(struct tiler_block *block)
{
	int ret = tcm_free(&block->area);

	if (block->area.tcm)
		dev_err(omap_dmm->dev, "failed to release block\n");

	spin_lock(&omap_dmm->list_lock);
	list_del(&block->alloc_node);
	spin_unlock(&omap_dmm->list_lock);

	kfree(block);
	return ret;
}

/*
 * Utils
 */

/* calculate the tiler space address of a pixel in a view orientation */
static u32 tiler_get_address(u32 orient, enum tiler_fmt fmt, u32 x, u32 y)
{
	u32 x_bits, y_bits, tmp, x_mask, y_mask, alignment;

	x_bits = CONT_WIDTH_BITS - geom[fmt].x_shft;
	y_bits = CONT_HEIGHT_BITS - geom[fmt].y_shft;
	alignment = geom[fmt].x_shft + geom[fmt].y_shft;

	/* validate coordinate */
	x_mask = MASK(x_bits);
	y_mask = MASK(y_bits);

	if (x < 0 || x > x_mask || y < 0 || y > y_mask)
		return 0;

	/* account for mirroring */
	if (orient & MASK_X_INVERT)
		x ^= x_mask;
	if (orient & MASK_Y_INVERT)
		y ^= y_mask;

	/* get coordinate address */
	if (orient & MASK_XY_FLIP)
		tmp = ((x << y_bits) + y);
	else
		tmp = ((y << x_bits) + x);

	return TIL_ADDR((tmp << alignment), orient, fmt);
}

dma_addr_t tiler_ssptr(struct tiler_block *block)
{
	BUG_ON(!validfmt(block->fmt));

	return TILVIEW_8BIT + tiler_get_address(0, block->fmt,
			block->area.p0.x * geom[block->fmt].slot_w,
			block->area.p0.y * geom[block->fmt].slot_h);
}

void tiler_align(enum tiler_fmt fmt, uint16_t *w, uint16_t *h)
{
	BUG_ON(!validfmt(fmt));
	*w = round_up(*w, geom[fmt].slot_w);
	*h = round_up(*h, geom[fmt].slot_h);
}

uint32_t tiler_stride(enum tiler_fmt fmt)
{
	BUG_ON(!validfmt(fmt));

	return 1 << (CONT_WIDTH_BITS + geom[fmt].y_shft);
}

size_t tiler_size(enum tiler_fmt fmt, uint16_t w, uint16_t h)
{
	tiler_align(fmt, &w, &h);
	return geom[fmt].cpp * w * h;
}

size_t tiler_vsize(enum tiler_fmt fmt, uint16_t w, uint16_t h)
{
	BUG_ON(!validfmt(fmt));
	return round_up(geom[fmt].cpp * w, PAGE_SIZE) * h;
}

int omap_dmm_remove(void)
{
	struct tiler_block *block, *_block;
	int i;

	if (omap_dmm) {
		/* free all area regions */
		spin_lock(&omap_dmm->list_lock);
		list_for_each_entry_safe(block, _block, &omap_dmm->alloc_head,
					alloc_node) {
			list_del(&block->alloc_node);
			kfree(block);
		}
		spin_unlock(&omap_dmm->list_lock);

		for (i = 0; i < omap_dmm->num_lut; i++)
			if (omap_dmm->tcm && omap_dmm->tcm[i])
				omap_dmm->tcm[i]->deinit(omap_dmm->tcm[i]);
		kfree(omap_dmm->tcm);

		kfree(omap_dmm->engines);
		if (omap_dmm->refill_va)
			dma_free_coherent(omap_dmm->dev,
				REFILL_BUFFER_SIZE * omap_dmm->num_engines,
				omap_dmm->refill_va,
				omap_dmm->refill_pa);
		if (omap_dmm->dummy_page)
			__free_page(omap_dmm->dummy_page);

		vfree(omap_dmm->lut);

		if (omap_dmm->irq != -1)
			free_irq(omap_dmm->irq, omap_dmm);

		kfree(omap_dmm);
	}

	return 0;
}

int omap_dmm_init(struct drm_device *dev)
{
	int ret = -EFAULT, i;
	struct tcm_area area = {0};
	u32 hwinfo, pat_geom, lut_table_size;
	struct omap_drm_platform_data *pdata = dev->dev->platform_data;

	if (!pdata || !pdata->dmm_pdata) {
		dev_err(dev->dev, "dmm platform data not present, skipping\n");
		return ret;
	}

	omap_dmm = kzalloc(sizeof(*omap_dmm), GFP_KERNEL);
	if (!omap_dmm) {
		dev_err(dev->dev, "failed to allocate driver data section\n");
		goto fail;
	}

	/* lookup hwmod data - base address and irq */
	omap_dmm->base = pdata->dmm_pdata->base;
	omap_dmm->irq = pdata->dmm_pdata->irq;
	omap_dmm->dev = dev->dev;

	if (!omap_dmm->base) {
		dev_err(dev->dev, "failed to get dmm base address\n");
		goto fail;
	}

	hwinfo = readl(omap_dmm->base + DMM_PAT_HWINFO);
	omap_dmm->num_engines = (hwinfo >> 24) & 0x1F;
	omap_dmm->num_lut = (hwinfo >> 16) & 0x1F;
	omap_dmm->container_width = 256;
	omap_dmm->container_height = 128;

	/* read out actual LUT width and height */
	pat_geom = readl(omap_dmm->base + DMM_PAT_GEOMETRY);
	omap_dmm->lut_width = ((pat_geom >> 16) & 0xF) << 5;
	omap_dmm->lut_height = ((pat_geom >> 24) & 0xF) << 5;

	/* initialize DMM registers */
	writel(0x88888888, omap_dmm->base + DMM_PAT_VIEW__0);
	writel(0x88888888, omap_dmm->base + DMM_PAT_VIEW__1);
	writel(0x80808080, omap_dmm->base + DMM_PAT_VIEW_MAP__0);
	writel(0x80000000, omap_dmm->base + DMM_PAT_VIEW_MAP_BASE);
	writel(0x88888888, omap_dmm->base + DMM_TILER_OR__0);
	writel(0x88888888, omap_dmm->base + DMM_TILER_OR__1);

	ret = request_irq(omap_dmm->irq, omap_dmm_irq_handler, IRQF_SHARED,
				"omap_dmm_irq_handler", omap_dmm);

	if (ret) {
		dev_err(dev->dev, "couldn't register IRQ %d, error %d\n",
			omap_dmm->irq, ret);
		omap_dmm->irq = -1;
		goto fail;
	}

	/* Enable all interrupts for each refill engine except
	 * ERR_LUT_MISS<n> (which is just advisory, and we don't care
	 * about because we want to be able to refill live scanout
	 * buffers for accelerated pan/scroll) and FILL_DSC<n> which
	 * we just generally don't care about.
	 */
	writel(0x7e7e7e7e, omap_dmm->base + DMM_PAT_IRQENABLE_SET);

	lut_table_size = omap_dmm->lut_width * omap_dmm->lut_height *
			omap_dmm->num_lut;

	omap_dmm->lut = vmalloc(lut_table_size * sizeof(*omap_dmm->lut));
	if (!omap_dmm->lut) {
		dev_err(dev->dev, "could not allocate lut table\n");
		ret = -ENOMEM;
		goto fail;
	}

	omap_dmm->dummy_page = alloc_page(GFP_KERNEL | __GFP_DMA32);
	if (!omap_dmm->dummy_page) {
		dev_err(dev->dev, "could not allocate dummy page\n");
		ret = -ENOMEM;
		goto fail;
	}
	omap_dmm->dummy_pa = page_to_phys(omap_dmm->dummy_page);

	/* alloc refill memory */
	omap_dmm->refill_va = dma_alloc_coherent(dev->dev,
				REFILL_BUFFER_SIZE * omap_dmm->num_engines,
				&omap_dmm->refill_pa, GFP_KERNEL);
	if (!omap_dmm->refill_va) {
		dev_err(dev->dev, "could not allocate refill memory\n");
		goto fail;
	}

	/* alloc engines */
	omap_dmm->engines = kzalloc(
			omap_dmm->num_engines * sizeof(struct refill_engine),
			GFP_KERNEL);
	if (!omap_dmm->engines) {
		dev_err(dev->dev, "could not allocate engines\n");
		ret = -ENOMEM;
		goto fail;
	}

	sema_init(&omap_dmm->engine_sem, omap_dmm->num_engines);
	INIT_LIST_HEAD(&omap_dmm->idle_head);
	for (i = 0; i < omap_dmm->num_engines; i++) {
		omap_dmm->engines[i].id = i;
		omap_dmm->engines[i].dmm = omap_dmm;
		omap_dmm->engines[i].refill_va = omap_dmm->refill_va +
						(REFILL_BUFFER_SIZE * i);
		omap_dmm->engines[i].refill_pa = omap_dmm->refill_pa +
						(REFILL_BUFFER_SIZE * i);
		init_waitqueue_head(&omap_dmm->engines[i].wait_for_refill);

		list_add(&omap_dmm->engines[i].idle_node, &omap_dmm->idle_head);
	}

	omap_dmm->tcm = kzalloc(omap_dmm->num_lut * sizeof(*omap_dmm->tcm),
				GFP_KERNEL);
	if (!omap_dmm->tcm) {
		dev_err(dev->dev, "failed to allocate lut ptrs\n");
		ret = -ENOMEM;
		goto fail;
	}

	/* init containers */
	for (i = 0; i < omap_dmm->num_lut; i++) {
		omap_dmm->tcm[i] = sita_init(omap_dmm->container_width,
						omap_dmm->container_height,
						NULL);

		if (!omap_dmm->tcm[i]) {
			dev_err(dev->dev, "failed to allocate container\n");
			ret = -ENOMEM;
			goto fail;
		}

		omap_dmm->tcm[i]->lut_id = i;
	}

	/* assign access mode containers to applicable tcm container */
	/* OMAP 4 has 1 container for all 4 views */
	containers[TILFMT_8BIT] = omap_dmm->tcm[0];
	containers[TILFMT_16BIT] = omap_dmm->tcm[0];
	containers[TILFMT_32BIT] = omap_dmm->tcm[0];
	containers[TILFMT_PAGE] = omap_dmm->tcm[0];

	INIT_LIST_HEAD(&omap_dmm->alloc_head);
	spin_lock_init(&omap_dmm->list_lock);

	area = (struct tcm_area) {
		.is2d = true,
		.tcm = NULL,
		.p1.x = omap_dmm->container_width - 1,
		.p1.y = omap_dmm->container_height - 1,
	};

	for (i = 0; i < lut_table_size; i++)
		omap_dmm->lut[i] = omap_dmm->dummy_pa;

	/* initialize all LUTs to dummy page entries */
	for (i = 0; i < omap_dmm->num_lut; i++) {
		area.tcm = omap_dmm->tcm[i];
		if (fill(&area, NULL, 0, 0, true))
			dev_err(omap_dmm->dev, "refill failed");
	}

	dev_info(omap_dmm->dev, "initialized all PAT entries\n");

	return 0;

fail:
	omap_dmm_remove();
	return ret;
}

/*
 * debugfs support
 */

#ifdef CONFIG_DEBUG_FS

static const char *alphabet = "abcdefghijklmnopqrstuvwxyz"
				"ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
static const char *special = ".,:;'\"`~!^-+";

static void fill_map(char **map, int xdiv, int ydiv, struct tcm_area *a,
							char c, bool ovw)
{
	int x, y;
	for (y = a->p0.y / ydiv; y <= a->p1.y / ydiv; y++)
		for (x = a->p0.x / xdiv; x <= a->p1.x / xdiv; x++)
			if (map[y][x] == ' ' || ovw)
				map[y][x] = c;
}

static void fill_map_pt(char **map, int xdiv, int ydiv, struct tcm_pt *p,
									char c)
{
	map[p->y / ydiv][p->x / xdiv] = c;
}

static char read_map_pt(char **map, int xdiv, int ydiv, struct tcm_pt *p)
{
	return map[p->y / ydiv][p->x / xdiv];
}

static int map_width(int xdiv, int x0, int x1)
{
	return (x1 / xdiv) - (x0 / xdiv) + 1;
}

static void text_map(char **map, int xdiv, char *nice, int yd, int x0, int x1)
{
	char *p = map[yd] + (x0 / xdiv);
	int w = (map_width(xdiv, x0, x1) - strlen(nice)) / 2;
	if (w >= 0) {
		p += w;
		while (*nice)
			*p++ = *nice++;
	}
}

static void map_1d_info(char **map, int xdiv, int ydiv, char *nice,
							struct tcm_area *a)
{
	sprintf(nice, "%dK", tcm_sizeof(*a) * 4);
	if (a->p0.y + 1 < a->p1.y) {
		text_map(map, xdiv, nice, (a->p0.y + a->p1.y) / 2 / ydiv, 0,
							256 - 1);
	} else if (a->p0.y < a->p1.y) {
		if (strlen(nice) < map_width(xdiv, a->p0.x, 256 - 1))
			text_map(map, xdiv, nice, a->p0.y / ydiv,
					a->p0.x + xdiv,	256 - 1);
		else if (strlen(nice) < map_width(xdiv, 0, a->p1.x))
			text_map(map, xdiv, nice, a->p1.y / ydiv,
					0, a->p1.y - xdiv);
	} else if (strlen(nice) + 1 < map_width(xdiv, a->p0.x, a->p1.x)) {
		text_map(map, xdiv, nice, a->p0.y / ydiv, a->p0.x, a->p1.x);
	}
}

static void map_2d_info(char **map, int xdiv, int ydiv, char *nice,
							struct tcm_area *a)
{
	sprintf(nice, "(%d*%d)", tcm_awidth(*a), tcm_aheight(*a));
	if (strlen(nice) + 1 < map_width(xdiv, a->p0.x, a->p1.x))
		text_map(map, xdiv, nice, (a->p0.y + a->p1.y) / 2 / ydiv,
							a->p0.x, a->p1.x);
}

int tiler_map_show(struct seq_file *s, void *arg)
{
	int xdiv = 2, ydiv = 1;
	char **map = NULL, *global_map;
	struct tiler_block *block;
	struct tcm_area a, p;
	int i;
	const char *m2d = alphabet;
	const char *a2d = special;
	const char *m2dp = m2d, *a2dp = a2d;
	char nice[128];
	int h_adj = omap_dmm->lut_height / ydiv;
	int w_adj = omap_dmm->lut_width / xdiv;
	unsigned long flags;

	map = kzalloc(h_adj * sizeof(*map), GFP_KERNEL);
	global_map = kzalloc((w_adj + 1) * h_adj, GFP_KERNEL);

	if (!map || !global_map)
		goto error;

	memset(global_map, ' ', (w_adj + 1) * h_adj);
	for (i = 0; i < omap_dmm->lut_height; i++) {
		map[i] = global_map + i * (w_adj + 1);
		map[i][w_adj] = 0;
	}
	spin_lock_irqsave(&omap_dmm->list_lock, flags);

	list_for_each_entry(block, &omap_dmm->alloc_head, alloc_node) {
		if (block->fmt != TILFMT_PAGE) {
			fill_map(map, xdiv, ydiv, &block->area, *m2dp, true);
			if (!*++a2dp)
				a2dp = a2d;
			if (!*++m2dp)
				m2dp = m2d;
			map_2d_info(map, xdiv, ydiv, nice, &block->area);
		} else {
			bool start = read_map_pt(map, xdiv, ydiv,
							&block->area.p0)
									== ' ';
			bool end = read_map_pt(map, xdiv, ydiv, &block->area.p1)
									== ' ';
			tcm_for_each_slice(a, block->area, p)
				fill_map(map, xdiv, ydiv, &a, '=', true);
			fill_map_pt(map, xdiv, ydiv, &block->area.p0,
							start ? '<' : 'X');
			fill_map_pt(map, xdiv, ydiv, &block->area.p1,
							end ? '>' : 'X');
			map_1d_info(map, xdiv, ydiv, nice, &block->area);
		}
	}

	spin_unlock_irqrestore(&omap_dmm->list_lock, flags);

	if (s) {
		seq_printf(s, "BEGIN DMM TILER MAP\n");
		for (i = 0; i < 128; i++)
			seq_printf(s, "%03d:%s\n", i, map[i]);
		seq_printf(s, "END TILER MAP\n");
	} else {
		dev_dbg(omap_dmm->dev, "BEGIN DMM TILER MAP\n");
		for (i = 0; i < 128; i++)
			dev_dbg(omap_dmm->dev, "%03d:%s\n", i, map[i]);
		dev_dbg(omap_dmm->dev, "END TILER MAP\n");
	}

error:
	kfree(map);
	kfree(global_map);

	return 0;
}
#endif