drm_buddy.c 26.2 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 32 33 34 35 36 37 38 39 40
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2021 Intel Corporation
 */

#include <linux/kmemleak.h>
#include <linux/module.h>
#include <linux/sizes.h>

#include <drm/drm_buddy.h>

static struct kmem_cache *slab_blocks;

static struct drm_buddy_block *drm_block_alloc(struct drm_buddy *mm,
					       struct drm_buddy_block *parent,
					       unsigned int order,
					       u64 offset)
{
	struct drm_buddy_block *block;

	BUG_ON(order > DRM_BUDDY_MAX_ORDER);

	block = kmem_cache_zalloc(slab_blocks, GFP_KERNEL);
	if (!block)
		return NULL;

	block->header = offset;
	block->header |= order;
	block->parent = parent;

	BUG_ON(block->header & DRM_BUDDY_HEADER_UNUSED);
	return block;
}

static void drm_block_free(struct drm_buddy *mm,
			   struct drm_buddy_block *block)
{
	kmem_cache_free(slab_blocks, block);
}

41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59
static void list_insert_sorted(struct drm_buddy *mm,
			       struct drm_buddy_block *block)
{
	struct drm_buddy_block *node;
	struct list_head *head;

	head = &mm->free_list[drm_buddy_block_order(block)];
	if (list_empty(head)) {
		list_add(&block->link, head);
		return;
	}

	list_for_each_entry(node, head, link)
		if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node))
			break;

	__list_add(&block->link, node->link.prev, &node->link);
}

60 61 62 63 64 65 66 67 68 69
static void clear_reset(struct drm_buddy_block *block)
{
	block->header &= ~DRM_BUDDY_HEADER_CLEAR;
}

static void mark_cleared(struct drm_buddy_block *block)
{
	block->header |= DRM_BUDDY_HEADER_CLEAR;
}

70 71 72 73 74 75 76 77 78 79 80 81 82 83
static void mark_allocated(struct drm_buddy_block *block)
{
	block->header &= ~DRM_BUDDY_HEADER_STATE;
	block->header |= DRM_BUDDY_ALLOCATED;

	list_del(&block->link);
}

static void mark_free(struct drm_buddy *mm,
		      struct drm_buddy_block *block)
{
	block->header &= ~DRM_BUDDY_HEADER_STATE;
	block->header |= DRM_BUDDY_FREE;

84
	list_insert_sorted(mm, block);
85 86 87 88 89 90 91 92 93 94
}

static void mark_split(struct drm_buddy_block *block)
{
	block->header &= ~DRM_BUDDY_HEADER_STATE;
	block->header |= DRM_BUDDY_SPLIT;

	list_del(&block->link);
}

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
static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2)
{
	return s1 <= e2 && e1 >= s2;
}

static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
{
	return s1 <= s2 && e1 >= e2;
}

static struct drm_buddy_block *
__get_buddy(struct drm_buddy_block *block)
{
	struct drm_buddy_block *parent;

	parent = block->parent;
	if (!parent)
		return NULL;

	if (parent->left == block)
		return parent->right;

	return parent->left;
}

static unsigned int __drm_buddy_free(struct drm_buddy *mm,
				     struct drm_buddy_block *block,
				     bool force_merge)
{
	struct drm_buddy_block *parent;
	unsigned int order;

	while ((parent = block->parent)) {
		struct drm_buddy_block *buddy;

		buddy = __get_buddy(block);

		if (!drm_buddy_block_is_free(buddy))
			break;

		if (!force_merge) {
			/*
			 * Check the block and its buddy clear state and exit
			 * the loop if they both have the dissimilar state.
			 */
			if (drm_buddy_block_is_clear(block) !=
			    drm_buddy_block_is_clear(buddy))
				break;

			if (drm_buddy_block_is_clear(block))
				mark_cleared(parent);
		}

		list_del(&buddy->link);
		if (force_merge && drm_buddy_block_is_clear(buddy))
			mm->clear_avail -= drm_buddy_block_size(mm, buddy);

		drm_block_free(mm, block);
		drm_block_free(mm, buddy);

		block = parent;
	}

	order = drm_buddy_block_order(block);
	mark_free(mm, block);

	return order;
}

static int __force_merge(struct drm_buddy *mm,
			 u64 start,
			 u64 end,
			 unsigned int min_order)
{
	unsigned int order;
	int i;

	if (!min_order)
		return -ENOMEM;

	if (min_order > mm->max_order)
		return -EINVAL;

	for (i = min_order - 1; i >= 0; i--) {
		struct drm_buddy_block *block, *prev;

		list_for_each_entry_safe_reverse(block, prev, &mm->free_list[i], link) {
			struct drm_buddy_block *buddy;
			u64 block_start, block_end;

			if (!block->parent)
				continue;

			block_start = drm_buddy_block_offset(block);
			block_end = block_start + drm_buddy_block_size(mm, block) - 1;

			if (!contains(start, end, block_start, block_end))
				continue;

			buddy = __get_buddy(block);
			if (!drm_buddy_block_is_free(buddy))
				continue;

			WARN_ON(drm_buddy_block_is_clear(block) ==
				drm_buddy_block_is_clear(buddy));

			/*
			 * If the prev block is same as buddy, don't access the
			 * block in the next iteration as we would free the
			 * buddy block as part of the free function.
			 */
			if (prev == buddy)
				prev = list_prev_entry(prev, link);

			list_del(&block->link);
			if (drm_buddy_block_is_clear(block))
				mm->clear_avail -= drm_buddy_block_size(mm, block);

			order = __drm_buddy_free(mm, block, true);
			if (order >= min_order)
				return 0;
		}
	}

	return -ENOMEM;
}

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
/**
 * drm_buddy_init - init memory manager
 *
 * @mm: DRM buddy manager to initialize
 * @size: size in bytes to manage
 * @chunk_size: minimum page size in bytes for our allocations
 *
 * Initializes the memory manager and its resources.
 *
 * Returns:
 * 0 on success, error code on failure.
 */
int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
{
	unsigned int i;
	u64 offset;

	if (size < chunk_size)
		return -EINVAL;

	if (chunk_size < PAGE_SIZE)
		return -EINVAL;

	if (!is_power_of_2(chunk_size))
		return -EINVAL;

	size = round_down(size, chunk_size);

	mm->size = size;
	mm->avail = size;
252
	mm->clear_avail = 0;
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
	mm->chunk_size = chunk_size;
	mm->max_order = ilog2(size) - ilog2(chunk_size);

	BUG_ON(mm->max_order > DRM_BUDDY_MAX_ORDER);

	mm->free_list = kmalloc_array(mm->max_order + 1,
				      sizeof(struct list_head),
				      GFP_KERNEL);
	if (!mm->free_list)
		return -ENOMEM;

	for (i = 0; i <= mm->max_order; ++i)
		INIT_LIST_HEAD(&mm->free_list[i]);

	mm->n_roots = hweight64(size);

	mm->roots = kmalloc_array(mm->n_roots,
				  sizeof(struct drm_buddy_block *),
				  GFP_KERNEL);
	if (!mm->roots)
		goto out_free_list;

	offset = 0;
	i = 0;

	/*
	 * Split into power-of-two blocks, in case we are given a size that is
	 * not itself a power-of-two.
	 */
	do {
		struct drm_buddy_block *root;
		unsigned int order;
		u64 root_size;

287 288
		order = ilog2(size) - ilog2(chunk_size);
		root_size = chunk_size << order;
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

		root = drm_block_alloc(mm, NULL, order, offset);
		if (!root)
			goto out_free_roots;

		mark_free(mm, root);

		BUG_ON(i > mm->max_order);
		BUG_ON(drm_buddy_block_size(mm, root) < chunk_size);

		mm->roots[i] = root;

		offset += root_size;
		size -= root_size;
		i++;
	} while (size);

	return 0;

out_free_roots:
	while (i--)
		drm_block_free(mm, mm->roots[i]);
	kfree(mm->roots);
out_free_list:
	kfree(mm->free_list);
	return -ENOMEM;
}
EXPORT_SYMBOL(drm_buddy_init);

/**
 * drm_buddy_fini - tear down the memory manager
 *
 * @mm: DRM buddy manager to free
 *
 * Cleanup memory manager resources and the freelist
 */
void drm_buddy_fini(struct drm_buddy *mm)
{
327 328
	u64 root_size, size;
	unsigned int order;
329 330
	int i;

331 332
	size = mm->size;

333
	for (i = 0; i < mm->n_roots; ++i) {
334 335 336
		order = ilog2(size) - ilog2(mm->chunk_size);
		__force_merge(mm, 0, size, order);

337 338
		WARN_ON(!drm_buddy_block_is_free(mm->roots[i]));
		drm_block_free(mm, mm->roots[i]);
339 340 341

		root_size = mm->chunk_size << order;
		size -= root_size;
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
	}

	WARN_ON(mm->avail != mm->size);

	kfree(mm->roots);
	kfree(mm->free_list);
}
EXPORT_SYMBOL(drm_buddy_fini);

static int split_block(struct drm_buddy *mm,
		       struct drm_buddy_block *block)
{
	unsigned int block_order = drm_buddy_block_order(block) - 1;
	u64 offset = drm_buddy_block_offset(block);

	BUG_ON(!drm_buddy_block_is_free(block));
	BUG_ON(!drm_buddy_block_order(block));

	block->left = drm_block_alloc(mm, block, block_order, offset);
	if (!block->left)
		return -ENOMEM;

	block->right = drm_block_alloc(mm, block, block_order,
				       offset + (mm->chunk_size << block_order));
	if (!block->right) {
		drm_block_free(mm, block->left);
		return -ENOMEM;
	}

	mark_free(mm, block->left);
	mark_free(mm, block->right);

374 375 376 377 378 379
	if (drm_buddy_block_is_clear(block)) {
		mark_cleared(block->left);
		mark_cleared(block->right);
		clear_reset(block);
	}

380 381 382 383 384
	mark_split(block);

	return 0;
}

385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401
/**
 * drm_get_buddy - get buddy address
 *
 * @block: DRM buddy block
 *
 * Returns the corresponding buddy block for @block, or NULL
 * if this is a root block and can't be merged further.
 * Requires some kind of locking to protect against
 * any concurrent allocate and free operations.
 */
struct drm_buddy_block *
drm_get_buddy(struct drm_buddy_block *block)
{
	return __get_buddy(block);
}
EXPORT_SYMBOL(drm_get_buddy);

402 403 404 405 406 407 408 409 410 411 412
/**
 * drm_buddy_free_block - free a block
 *
 * @mm: DRM buddy manager
 * @block: block to be freed
 */
void drm_buddy_free_block(struct drm_buddy *mm,
			  struct drm_buddy_block *block)
{
	BUG_ON(!drm_buddy_block_is_allocated(block));
	mm->avail += drm_buddy_block_size(mm, block);
413 414 415 416
	if (drm_buddy_block_is_clear(block))
		mm->clear_avail += drm_buddy_block_size(mm, block);

	__drm_buddy_free(mm, block, false);
417 418 419
}
EXPORT_SYMBOL(drm_buddy_free_block);

420 421 422 423
static void __drm_buddy_free_list(struct drm_buddy *mm,
				  struct list_head *objects,
				  bool mark_clear,
				  bool mark_dirty)
424 425 426
{
	struct drm_buddy_block *block, *on;

427 428
	WARN_ON(mark_dirty && mark_clear);

429
	list_for_each_entry_safe(block, on, objects, link) {
430 431 432 433
		if (mark_clear)
			mark_cleared(block);
		else if (mark_dirty)
			clear_reset(block);
434 435 436 437 438 439
		drm_buddy_free_block(mm, block);
		cond_resched();
	}
	INIT_LIST_HEAD(objects);
}

440 441
static void drm_buddy_free_list_internal(struct drm_buddy *mm,
					 struct list_head *objects)
442
{
443 444 445 446 447 448
	/*
	 * Don't touch the clear/dirty bit, since allocation is still internal
	 * at this point. For example we might have just failed part of the
	 * allocation.
	 */
	__drm_buddy_free_list(mm, objects, false, false);
449 450
}

451 452 453 454 455 456 457 458 459 460
/**
 * drm_buddy_free_list - free blocks
 *
 * @mm: DRM buddy manager
 * @objects: input list head to free blocks
 * @flags: optional flags like DRM_BUDDY_CLEARED
 */
void drm_buddy_free_list(struct drm_buddy *mm,
			 struct list_head *objects,
			 unsigned int flags)
461
{
462 463 464 465 466 467 468 469 470 471 472
	bool mark_clear = flags & DRM_BUDDY_CLEARED;

	__drm_buddy_free_list(mm, objects, mark_clear, !mark_clear);
}
EXPORT_SYMBOL(drm_buddy_free_list);

static bool block_incompatible(struct drm_buddy_block *block, unsigned int flags)
{
	bool needs_clear = flags & DRM_BUDDY_CLEAR_ALLOCATION;

	return needs_clear != drm_buddy_block_is_clear(block);
473 474 475
}

static struct drm_buddy_block *
476 477 478 479 480
__alloc_range_bias(struct drm_buddy *mm,
		   u64 start, u64 end,
		   unsigned int order,
		   unsigned long flags,
		   bool fallback)
481
{
Matthew Auld's avatar
Matthew Auld committed
482
	u64 req_size = mm->chunk_size << order;
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
	struct drm_buddy_block *block;
	struct drm_buddy_block *buddy;
	LIST_HEAD(dfs);
	int err;
	int i;

	end = end - 1;

	for (i = 0; i < mm->n_roots; ++i)
		list_add_tail(&mm->roots[i]->tmp_link, &dfs);

	do {
		u64 block_start;
		u64 block_end;

		block = list_first_entry_or_null(&dfs,
						 struct drm_buddy_block,
						 tmp_link);
		if (!block)
			break;

		list_del(&block->tmp_link);

		if (drm_buddy_block_order(block) < order)
			continue;

		block_start = drm_buddy_block_offset(block);
		block_end = block_start + drm_buddy_block_size(mm, block) - 1;

		if (!overlaps(start, end, block_start, block_end))
			continue;

		if (drm_buddy_block_is_allocated(block))
			continue;

Matthew Auld's avatar
Matthew Auld committed
518 519 520 521 522 523 524 525 526
		if (block_start < start || block_end > end) {
			u64 adjusted_start = max(block_start, start);
			u64 adjusted_end = min(block_end, end);

			if (round_down(adjusted_end + 1, req_size) <=
			    round_up(adjusted_start, req_size))
				continue;
		}

527 528
		if (contains(start, end, block_start, block_end) &&
		    order == drm_buddy_block_order(block)) {
529 530 531
			if (!fallback && block_incompatible(block, flags))
				continue;

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
			/*
			 * Find the free block within the range.
			 */
			if (drm_buddy_block_is_free(block))
				return block;

			continue;
		}

		if (!drm_buddy_block_is_split(block)) {
			err = split_block(mm, block);
			if (unlikely(err))
				goto err_undo;
		}

		list_add(&block->right->tmp_link, &dfs);
		list_add(&block->left->tmp_link, &dfs);
	} while (1);

	return ERR_PTR(-ENOSPC);

err_undo:
	/*
	 * We really don't want to leave around a bunch of split blocks, since
	 * bigger is better, so make sure we merge everything back before we
	 * free the allocated blocks.
	 */
559
	buddy = __get_buddy(block);
560 561 562
	if (buddy &&
	    (drm_buddy_block_is_free(block) &&
	     drm_buddy_block_is_free(buddy)))
563
		__drm_buddy_free(mm, block, false);
564 565 566
	return ERR_PTR(err);
}

567
static struct drm_buddy_block *
568 569 570 571 572 573 574 575 576 577
__drm_buddy_alloc_range_bias(struct drm_buddy *mm,
			     u64 start, u64 end,
			     unsigned int order,
			     unsigned long flags)
{
	struct drm_buddy_block *block;
	bool fallback = false;

	block = __alloc_range_bias(mm, start, end, order,
				   flags, fallback);
578
	if (IS_ERR(block))
579 580 581 582 583 584 585 586 587
		return __alloc_range_bias(mm, start, end, order,
					  flags, !fallback);

	return block;
}

static struct drm_buddy_block *
get_maxblock(struct drm_buddy *mm, unsigned int order,
	     unsigned long flags)
588
{
589
	struct drm_buddy_block *max_block = NULL, *block = NULL;
590
	unsigned int i;
591

592
	for (i = order; i <= mm->max_order; ++i) {
593 594 595 596
		struct drm_buddy_block *tmp_block;

		list_for_each_entry_reverse(tmp_block, &mm->free_list[i], link) {
			if (block_incompatible(tmp_block, flags))
597 598
				continue;

599 600 601 602 603 604 605 606 607 608 609 610 611 612 613
			block = tmp_block;
			break;
		}

		if (!block)
			continue;

		if (!max_block) {
			max_block = block;
			continue;
		}

		if (drm_buddy_block_offset(block) >
		    drm_buddy_block_offset(max_block)) {
			max_block = block;
614
		}
615 616 617 618 619
	}

	return max_block;
}

620 621 622 623
static struct drm_buddy_block *
alloc_from_freelist(struct drm_buddy *mm,
		    unsigned int order,
		    unsigned long flags)
624 625
{
	struct drm_buddy_block *block = NULL;
626
	unsigned int tmp;
627 628
	int err;

629
	if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
630
		block = get_maxblock(mm, order, flags);
631 632 633 634
		if (block)
			/* Store the obtained block order */
			tmp = drm_buddy_block_order(block);
	} else {
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652
		for (tmp = order; tmp <= mm->max_order; ++tmp) {
			struct drm_buddy_block *tmp_block;

			list_for_each_entry_reverse(tmp_block, &mm->free_list[tmp], link) {
				if (block_incompatible(tmp_block, flags))
					continue;

				block = tmp_block;
				break;
			}

			if (block)
				break;
		}
	}

	if (!block) {
		/* Fallback method */
653 654 655 656 657 658 659 660
		for (tmp = order; tmp <= mm->max_order; ++tmp) {
			if (!list_empty(&mm->free_list[tmp])) {
				block = list_last_entry(&mm->free_list[tmp],
							struct drm_buddy_block,
							link);
				if (block)
					break;
			}
661
		}
662

663 664 665
		if (!block)
			return ERR_PTR(-ENOSPC);
	}
666 667 668

	BUG_ON(!drm_buddy_block_is_free(block));

669
	while (tmp != order) {
670 671
		err = split_block(mm, block);
		if (unlikely(err))
672
			goto err_undo;
673

674
		block = block->right;
675
		tmp--;
676 677 678
	}
	return block;

679
err_undo:
680
	if (tmp != order)
681
		__drm_buddy_free(mm, block, false);
682 683 684
	return ERR_PTR(err);
}

685 686 687
static int __alloc_range(struct drm_buddy *mm,
			 struct list_head *dfs,
			 u64 start, u64 size,
688 689
			 struct list_head *blocks,
			 u64 *total_allocated_on_err)
690 691 692
{
	struct drm_buddy_block *block;
	struct drm_buddy_block *buddy;
693
	u64 total_allocated = 0;
694 695 696 697 698 699 700 701 702 703
	LIST_HEAD(allocated);
	u64 end;
	int err;

	end = start + size - 1;

	do {
		u64 block_start;
		u64 block_end;

704
		block = list_first_entry_or_null(dfs,
705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
						 struct drm_buddy_block,
						 tmp_link);
		if (!block)
			break;

		list_del(&block->tmp_link);

		block_start = drm_buddy_block_offset(block);
		block_end = block_start + drm_buddy_block_size(mm, block) - 1;

		if (!overlaps(start, end, block_start, block_end))
			continue;

		if (drm_buddy_block_is_allocated(block)) {
			err = -ENOSPC;
			goto err_free;
		}

		if (contains(start, end, block_start, block_end)) {
724 725 726 727 728 729 730 731 732
			if (drm_buddy_block_is_free(block)) {
				mark_allocated(block);
				total_allocated += drm_buddy_block_size(mm, block);
				mm->avail -= drm_buddy_block_size(mm, block);
				if (drm_buddy_block_is_clear(block))
					mm->clear_avail -= drm_buddy_block_size(mm, block);
				list_add_tail(&block->link, &allocated);
				continue;
			} else if (!mm->clear_avail) {
733 734 735 736 737 738 739 740 741 742 743
				err = -ENOSPC;
				goto err_free;
			}
		}

		if (!drm_buddy_block_is_split(block)) {
			err = split_block(mm, block);
			if (unlikely(err))
				goto err_undo;
		}

744 745
		list_add(&block->right->tmp_link, dfs);
		list_add(&block->left->tmp_link, dfs);
746 747
	} while (1);

748 749 750 751 752
	if (total_allocated < size) {
		err = -ENOSPC;
		goto err_free;
	}

753 754
	list_splice_tail(&allocated, blocks);

755 756 757 758 759 760 761 762
	return 0;

err_undo:
	/*
	 * We really don't want to leave around a bunch of split blocks, since
	 * bigger is better, so make sure we merge everything back before we
	 * free the allocated blocks.
	 */
763
	buddy = __get_buddy(block);
764 765 766
	if (buddy &&
	    (drm_buddy_block_is_free(block) &&
	     drm_buddy_block_is_free(buddy)))
767
		__drm_buddy_free(mm, block, false);
768 769

err_free:
770 771 772 773
	if (err == -ENOSPC && total_allocated_on_err) {
		list_splice_tail(&allocated, blocks);
		*total_allocated_on_err = total_allocated;
	} else {
774
		drm_buddy_free_list_internal(mm, &allocated);
775 776
	}

777 778
	return err;
}
779 780 781 782

static int __drm_buddy_alloc_range(struct drm_buddy *mm,
				   u64 start,
				   u64 size,
783
				   u64 *total_allocated_on_err,
784 785 786 787 788 789 790 791
				   struct list_head *blocks)
{
	LIST_HEAD(dfs);
	int i;

	for (i = 0; i < mm->n_roots; ++i)
		list_add_tail(&mm->roots[i]->tmp_link, &dfs);

792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839
	return __alloc_range(mm, &dfs, start, size,
			     blocks, total_allocated_on_err);
}

static int __alloc_contig_try_harder(struct drm_buddy *mm,
				     u64 size,
				     u64 min_block_size,
				     struct list_head *blocks)
{
	u64 rhs_offset, lhs_offset, lhs_size, filled;
	struct drm_buddy_block *block;
	struct list_head *list;
	LIST_HEAD(blocks_lhs);
	unsigned long pages;
	unsigned int order;
	u64 modify_size;
	int err;

	modify_size = rounddown_pow_of_two(size);
	pages = modify_size >> ilog2(mm->chunk_size);
	order = fls(pages) - 1;
	if (order == 0)
		return -ENOSPC;

	list = &mm->free_list[order];
	if (list_empty(list))
		return -ENOSPC;

	list_for_each_entry_reverse(block, list, link) {
		/* Allocate blocks traversing RHS */
		rhs_offset = drm_buddy_block_offset(block);
		err =  __drm_buddy_alloc_range(mm, rhs_offset, size,
					       &filled, blocks);
		if (!err || err != -ENOSPC)
			return err;

		lhs_size = max((size - filled), min_block_size);
		if (!IS_ALIGNED(lhs_size, min_block_size))
			lhs_size = round_up(lhs_size, min_block_size);

		/* Allocate blocks traversing LHS */
		lhs_offset = drm_buddy_block_offset(block) - lhs_size;
		err =  __drm_buddy_alloc_range(mm, lhs_offset, lhs_size,
					       NULL, &blocks_lhs);
		if (!err) {
			list_splice(&blocks_lhs, blocks);
			return 0;
		} else if (err != -ENOSPC) {
840
			drm_buddy_free_list_internal(mm, blocks);
841 842 843
			return err;
		}
		/* Free blocks for the next iteration */
844
		drm_buddy_free_list_internal(mm, blocks);
845 846 847
	}

	return -ENOSPC;
848 849
}

850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899
/**
 * drm_buddy_block_trim - free unused pages
 *
 * @mm: DRM buddy manager
 * @new_size: original size requested
 * @blocks: Input and output list of allocated blocks.
 * MUST contain single block as input to be trimmed.
 * On success will contain the newly allocated blocks
 * making up the @new_size. Blocks always appear in
 * ascending order
 *
 * For contiguous allocation, we round up the size to the nearest
 * power of two value, drivers consume *actual* size, so remaining
 * portions are unused and can be optionally freed with this function
 *
 * Returns:
 * 0 on success, error code on failure.
 */
int drm_buddy_block_trim(struct drm_buddy *mm,
			 u64 new_size,
			 struct list_head *blocks)
{
	struct drm_buddy_block *parent;
	struct drm_buddy_block *block;
	LIST_HEAD(dfs);
	u64 new_start;
	int err;

	if (!list_is_singular(blocks))
		return -EINVAL;

	block = list_first_entry(blocks,
				 struct drm_buddy_block,
				 link);

	if (WARN_ON(!drm_buddy_block_is_allocated(block)))
		return -EINVAL;

	if (new_size > drm_buddy_block_size(mm, block))
		return -EINVAL;

	if (!new_size || !IS_ALIGNED(new_size, mm->chunk_size))
		return -EINVAL;

	if (new_size == drm_buddy_block_size(mm, block))
		return 0;

	list_del(&block->link);
	mark_free(mm, block);
	mm->avail += drm_buddy_block_size(mm, block);
900 901
	if (drm_buddy_block_is_clear(block))
		mm->clear_avail += drm_buddy_block_size(mm, block);
902 903 904 905 906 907 908

	/* Prevent recursively freeing this node */
	parent = block->parent;
	block->parent = NULL;

	new_start = drm_buddy_block_offset(block);
	list_add(&block->tmp_link, &dfs);
909
	err =  __alloc_range(mm, &dfs, new_start, new_size, blocks, NULL);
910 911 912
	if (err) {
		mark_allocated(block);
		mm->avail -= drm_buddy_block_size(mm, block);
913 914
		if (drm_buddy_block_is_clear(block))
			mm->clear_avail -= drm_buddy_block_size(mm, block);
915 916 917 918 919 920 921 922
		list_add(&block->link, blocks);
	}

	block->parent = parent;
	return err;
}
EXPORT_SYMBOL(drm_buddy_block_trim);

923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
static struct drm_buddy_block *
__drm_buddy_alloc_blocks(struct drm_buddy *mm,
			 u64 start, u64 end,
			 unsigned int order,
			 unsigned long flags)
{
	if (flags & DRM_BUDDY_RANGE_ALLOCATION)
		/* Allocate traversing within the range */
		return  __drm_buddy_alloc_range_bias(mm, start, end,
						     order, flags);
	else
		/* Allocate from freelist */
		return alloc_from_freelist(mm, order, flags);
}

938 939 940 941 942 943
/**
 * drm_buddy_alloc_blocks - allocate power-of-two blocks
 *
 * @mm: DRM buddy manager to allocate from
 * @start: start of the allowed range for this block
 * @end: end of the allowed range for this block
944
 * @size: size of the allocation in bytes
945
 * @min_block_size: alignment of the allocation
946 947 948 949 950 951 952 953 954 955 956 957 958 959
 * @blocks: output list head to add allocated blocks
 * @flags: DRM_BUDDY_*_ALLOCATION flags
 *
 * alloc_range_bias() called on range limitations, which traverses
 * the tree and returns the desired block.
 *
 * alloc_from_freelist() called when *no* range restrictions
 * are enforced, which picks the block from the freelist.
 *
 * Returns:
 * 0 on success, error code on failure.
 */
int drm_buddy_alloc_blocks(struct drm_buddy *mm,
			   u64 start, u64 end, u64 size,
960
			   u64 min_block_size,
961 962 963 964
			   struct list_head *blocks,
			   unsigned long flags)
{
	struct drm_buddy_block *block = NULL;
965
	u64 original_size, original_min_size;
966 967
	unsigned int min_order, order;
	LIST_HEAD(allocated);
968
	unsigned long pages;
969 970 971 972 973
	int err;

	if (size < mm->chunk_size)
		return -EINVAL;

974
	if (min_block_size < mm->chunk_size)
975 976
		return -EINVAL;

977
	if (!is_power_of_2(min_block_size))
978 979 980 981 982 983 984 985 986 987 988 989
		return -EINVAL;

	if (!IS_ALIGNED(start | end | size, mm->chunk_size))
		return -EINVAL;

	if (end > mm->size)
		return -EINVAL;

	if (range_overflows(start, size, mm->size))
		return -EINVAL;

	/* Actual range allocation */
990 991 992 993
	if (start + size == end) {
		if (!IS_ALIGNED(start | end, min_block_size))
			return -EINVAL;

994
		return __drm_buddy_alloc_range(mm, start, size, NULL, blocks);
995
	}
996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007

	original_size = size;
	original_min_size = min_block_size;

	/* Roundup the size to power of 2 */
	if (flags & DRM_BUDDY_CONTIGUOUS_ALLOCATION) {
		size = roundup_pow_of_two(size);
		min_block_size = size;
	/* Align size value to min_block_size */
	} else if (!IS_ALIGNED(size, min_block_size)) {
		size = round_up(size, min_block_size);
	}
1008

1009 1010
	pages = size >> ilog2(mm->chunk_size);
	order = fls(pages) - 1;
1011
	min_order = ilog2(min_block_size) - ilog2(mm->chunk_size);
1012 1013 1014 1015 1016 1017 1018

	do {
		order = min(order, (unsigned int)fls(pages) - 1);
		BUG_ON(order > mm->max_order);
		BUG_ON(order < min_order);

		do {
1019 1020 1021 1022
			block = __drm_buddy_alloc_blocks(mm, start,
							 end,
							 order,
							 flags);
1023 1024 1025 1026
			if (!IS_ERR(block))
				break;

			if (order-- == min_order) {
1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
				/* Try allocation through force merge method */
				if (mm->clear_avail &&
				    !__force_merge(mm, start, end, min_order)) {
					block = __drm_buddy_alloc_blocks(mm, start,
									 end,
									 min_order,
									 flags);
					if (!IS_ERR(block)) {
						order = min_order;
						break;
					}
				}

				/*
				 * Try contiguous block allocation through
				 * try harder method.
				 */
1044 1045 1046 1047 1048 1049
				if (flags & DRM_BUDDY_CONTIGUOUS_ALLOCATION &&
				    !(flags & DRM_BUDDY_RANGE_ALLOCATION))
					return __alloc_contig_try_harder(mm,
									 original_size,
									 original_min_size,
									 blocks);
1050 1051 1052 1053 1054 1055 1056
				err = -ENOSPC;
				goto err_free;
			}
		} while (1);

		mark_allocated(block);
		mm->avail -= drm_buddy_block_size(mm, block);
1057 1058
		if (drm_buddy_block_is_clear(block))
			mm->clear_avail -= drm_buddy_block_size(mm, block);
1059 1060 1061 1062 1063 1064 1065 1066 1067
		kmemleak_update_trace(block);
		list_add_tail(&block->link, &allocated);

		pages -= BIT(order);

		if (!pages)
			break;
	} while (1);

1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
	/* Trim the allocated block to the required size */
	if (original_size != size) {
		struct list_head *trim_list;
		LIST_HEAD(temp);
		u64 trim_size;

		trim_list = &allocated;
		trim_size = original_size;

		if (!list_is_singular(&allocated)) {
			block = list_last_entry(&allocated, typeof(*block), link);
			list_move(&block->link, &temp);
			trim_list = &temp;
			trim_size = drm_buddy_block_size(mm, block) -
				(size - original_size);
		}

		drm_buddy_block_trim(mm,
				     trim_size,
				     trim_list);

		if (!list_empty(&temp))
			list_splice_tail(trim_list, &allocated);
	}

1093 1094 1095 1096
	list_splice_tail(&allocated, blocks);
	return 0;

err_free:
1097
	drm_buddy_free_list_internal(mm, &allocated);
1098 1099 1100
	return err;
}
EXPORT_SYMBOL(drm_buddy_alloc_blocks);
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

/**
 * drm_buddy_block_print - print block information
 *
 * @mm: DRM buddy manager
 * @block: DRM buddy block
 * @p: DRM printer to use
 */
void drm_buddy_block_print(struct drm_buddy *mm,
			   struct drm_buddy_block *block,
			   struct drm_printer *p)
{
	u64 start = drm_buddy_block_offset(block);
	u64 size = drm_buddy_block_size(mm, block);

	drm_printf(p, "%#018llx-%#018llx: %llu\n", start, start + size, size);
}
EXPORT_SYMBOL(drm_buddy_block_print);

/**
 * drm_buddy_print - print allocator state
 *
 * @mm: DRM buddy manager
 * @p: DRM printer to use
 */
void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p)
{
	int order;

1130 1131
	drm_printf(p, "chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB, clear_free: %lluMiB\n",
		   mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
1132 1133 1134 1135 1136 1137 1138 1139 1140 1141

	for (order = mm->max_order; order >= 0; order--) {
		struct drm_buddy_block *block;
		u64 count = 0, free;

		list_for_each_entry(block, &mm->free_list[order], link) {
			BUG_ON(!drm_buddy_block_is_free(block));
			count++;
		}

1142
		drm_printf(p, "order-%2d ", order);
1143 1144 1145

		free = count * (mm->chunk_size << order);
		if (free < SZ_1M)
1146
			drm_printf(p, "free: %8llu KiB", free >> 10);
1147
		else
1148
			drm_printf(p, "free: %8llu MiB", free >> 20);
1149

1150
		drm_printf(p, ", blocks: %llu\n", count);
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
	}
}
EXPORT_SYMBOL(drm_buddy_print);

static void drm_buddy_module_exit(void)
{
	kmem_cache_destroy(slab_blocks);
}

static int __init drm_buddy_module_init(void)
{
	slab_blocks = KMEM_CACHE(drm_buddy_block, 0);
	if (!slab_blocks)
		return -ENOMEM;

	return 0;
}

module_init(drm_buddy_module_init);
module_exit(drm_buddy_module_exit);

MODULE_DESCRIPTION("DRM Buddy Allocator");
MODULE_LICENSE("Dual MIT/GPL");