delayed-ref.c 25.6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
/*
 * Copyright (C) 2009 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include "ctree.h"
#include "delayed-ref.h"
#include "transaction.h"

struct kmem_cache *btrfs_delayed_ref_head_cachep;
struct kmem_cache *btrfs_delayed_tree_ref_cachep;
struct kmem_cache *btrfs_delayed_data_ref_cachep;
struct kmem_cache *btrfs_delayed_extent_op_cachep;
/*
 * delayed back reference update tracking.  For subvolume trees
 * we queue up extent allocations and backref maintenance for
 * delayed processing.   This avoids deep call chains where we
 * add extents in the middle of btrfs_search_slot, and it allows
 * us to buffer up frequently modified backrefs in an rb tree instead
 * of hammering updates on the extent allocation tree.
 */

/*
 * compare two delayed tree backrefs with same bytenr and type
 */
static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref2,
			  struct btrfs_delayed_tree_ref *ref1, int type)
{
	if (type == BTRFS_TREE_BLOCK_REF_KEY) {
		if (ref1->root < ref2->root)
			return -1;
		if (ref1->root > ref2->root)
			return 1;
	} else {
		if (ref1->parent < ref2->parent)
			return -1;
		if (ref1->parent > ref2->parent)
			return 1;
	}
	return 0;
}

/*
 * compare two delayed data backrefs with same bytenr and type
 */
static int comp_data_refs(struct btrfs_delayed_data_ref *ref2,
			  struct btrfs_delayed_data_ref *ref1)
{
	if (ref1->node.type == BTRFS_EXTENT_DATA_REF_KEY) {
		if (ref1->root < ref2->root)
			return -1;
		if (ref1->root > ref2->root)
			return 1;
		if (ref1->objectid < ref2->objectid)
			return -1;
		if (ref1->objectid > ref2->objectid)
			return 1;
		if (ref1->offset < ref2->offset)
			return -1;
		if (ref1->offset > ref2->offset)
			return 1;
	} else {
		if (ref1->parent < ref2->parent)
			return -1;
		if (ref1->parent > ref2->parent)
			return 1;
	}
	return 0;
}

/*
 * entries in the rb tree are ordered by the byte number of the extent,
 * type of the delayed backrefs and content of delayed backrefs.
 */
static int comp_entry(struct btrfs_delayed_ref_node *ref2,
		      struct btrfs_delayed_ref_node *ref1,
		      bool compare_seq)
{
	if (ref1->bytenr < ref2->bytenr)
		return -1;
	if (ref1->bytenr > ref2->bytenr)
		return 1;
	if (ref1->is_head && ref2->is_head)
		return 0;
	if (ref2->is_head)
		return -1;
	if (ref1->is_head)
		return 1;
	if (ref1->type < ref2->type)
		return -1;
	if (ref1->type > ref2->type)
		return 1;
	/* merging of sequenced refs is not allowed */
	if (compare_seq) {
		if (ref1->seq < ref2->seq)
			return -1;
		if (ref1->seq > ref2->seq)
			return 1;
	}
	if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY ||
	    ref1->type == BTRFS_SHARED_BLOCK_REF_KEY) {
		return comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref2),
				      btrfs_delayed_node_to_tree_ref(ref1),
				      ref1->type);
	} else if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY ||
		   ref1->type == BTRFS_SHARED_DATA_REF_KEY) {
		return comp_data_refs(btrfs_delayed_node_to_data_ref(ref2),
				      btrfs_delayed_node_to_data_ref(ref1));
	}
	BUG();
	return 0;
}

/*
 * insert a new ref into the rbtree.  This returns any existing refs
 * for the same (bytenr,parent) tuple, or NULL if the new node was properly
 * inserted.
 */
static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root,
						  struct rb_node *node)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent_node = NULL;
	struct btrfs_delayed_ref_node *entry;
	struct btrfs_delayed_ref_node *ins;
	int cmp;

	ins = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
	while (*p) {
		parent_node = *p;
		entry = rb_entry(parent_node, struct btrfs_delayed_ref_node,
				 rb_node);

		cmp = comp_entry(entry, ins, 1);
		if (cmp < 0)
			p = &(*p)->rb_left;
		else if (cmp > 0)
			p = &(*p)->rb_right;
		else
			return entry;
	}

	rb_link_node(node, parent_node, p);
	rb_insert_color(node, root);
	return NULL;
}

/* insert a new ref to head ref rbtree */
static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
						   struct rb_node *node)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent_node = NULL;
	struct btrfs_delayed_ref_head *entry;
	struct btrfs_delayed_ref_head *ins;
	u64 bytenr;

	ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node);
	bytenr = ins->node.bytenr;
	while (*p) {
		parent_node = *p;
		entry = rb_entry(parent_node, struct btrfs_delayed_ref_head,
				 href_node);

		if (bytenr < entry->node.bytenr)
			p = &(*p)->rb_left;
		else if (bytenr > entry->node.bytenr)
			p = &(*p)->rb_right;
		else
			return entry;
	}

	rb_link_node(node, parent_node, p);
	rb_insert_color(node, root);
	return NULL;
}

/*
 * find an head entry based on bytenr. This returns the delayed ref
 * head if it was able to find one, or NULL if nothing was in that spot.
 * If return_bigger is given, the next bigger entry is returned if no exact
 * match is found.
 */
static struct btrfs_delayed_ref_head *
find_ref_head(struct rb_root *root, u64 bytenr,
	      struct btrfs_delayed_ref_head **last, int return_bigger)
{
	struct rb_node *n;
	struct btrfs_delayed_ref_head *entry;
	int cmp = 0;

again:
	n = root->rb_node;
	entry = NULL;
	while (n) {
		entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
		if (last)
			*last = entry;

		if (bytenr < entry->node.bytenr)
			cmp = -1;
		else if (bytenr > entry->node.bytenr)
			cmp = 1;
		else
			cmp = 0;

		if (cmp < 0)
			n = n->rb_left;
		else if (cmp > 0)
			n = n->rb_right;
		else
			return entry;
	}
	if (entry && return_bigger) {
		if (cmp > 0) {
			n = rb_next(&entry->href_node);
			if (!n)
				n = rb_first(root);
			entry = rb_entry(n, struct btrfs_delayed_ref_head,
					 href_node);
			bytenr = entry->node.bytenr;
			return_bigger = 0;
			goto again;
		}
		return entry;
	}
	return NULL;
}

int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
			   struct btrfs_delayed_ref_head *head)
{
	struct btrfs_delayed_ref_root *delayed_refs;

	delayed_refs = &trans->transaction->delayed_refs;
	assert_spin_locked(&delayed_refs->lock);
	if (mutex_trylock(&head->mutex))
		return 0;

	atomic_inc(&head->node.refs);
	spin_unlock(&delayed_refs->lock);

	mutex_lock(&head->mutex);
	spin_lock(&delayed_refs->lock);
	if (!head->node.in_tree) {
		mutex_unlock(&head->mutex);
		btrfs_put_delayed_ref(&head->node);
		return -EAGAIN;
	}
	btrfs_put_delayed_ref(&head->node);
	return 0;
}

static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
				    struct btrfs_delayed_ref_root *delayed_refs,
				    struct btrfs_delayed_ref_head *head,
				    struct btrfs_delayed_ref_node *ref)
{
	if (btrfs_delayed_ref_is_head(ref)) {
		head = btrfs_delayed_node_to_head(ref);
		rb_erase(&head->href_node, &delayed_refs->href_root);
	} else {
		assert_spin_locked(&head->lock);
		rb_erase(&ref->rb_node, &head->ref_root);
	}
	ref->in_tree = 0;
	btrfs_put_delayed_ref(ref);
	atomic_dec(&delayed_refs->num_entries);
	if (trans->delayed_ref_updates)
		trans->delayed_ref_updates--;
}

static int merge_ref(struct btrfs_trans_handle *trans,
		     struct btrfs_delayed_ref_root *delayed_refs,
		     struct btrfs_delayed_ref_head *head,
		     struct btrfs_delayed_ref_node *ref, u64 seq)
{
	struct rb_node *node;
	int mod = 0;
	int done = 0;

	node = rb_next(&ref->rb_node);
	while (!done && node) {
		struct btrfs_delayed_ref_node *next;

		next = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
		node = rb_next(node);
		if (seq && next->seq >= seq)
			break;
		if (comp_entry(ref, next, 0))
			continue;

		if (ref->action == next->action) {
			mod = next->ref_mod;
		} else {
			if (ref->ref_mod < next->ref_mod) {
				struct btrfs_delayed_ref_node *tmp;

				tmp = ref;
				ref = next;
				next = tmp;
				done = 1;
			}
			mod = -next->ref_mod;
		}

		drop_delayed_ref(trans, delayed_refs, head, next);
		ref->ref_mod += mod;
		if (ref->ref_mod == 0) {
			drop_delayed_ref(trans, delayed_refs, head, ref);
			done = 1;
		} else {
			/*
			 * You can't have multiples of the same ref on a tree
			 * block.
			 */
			WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
				ref->type == BTRFS_SHARED_BLOCK_REF_KEY);
		}
	}
	return done;
}

void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
			      struct btrfs_fs_info *fs_info,
			      struct btrfs_delayed_ref_root *delayed_refs,
			      struct btrfs_delayed_ref_head *head)
{
	struct rb_node *node;
	u64 seq = 0;

	assert_spin_locked(&head->lock);
	/*
	 * We don't have too much refs to merge in the case of delayed data
	 * refs.
	 */
	if (head->is_data)
		return;

	spin_lock(&fs_info->tree_mod_seq_lock);
	if (!list_empty(&fs_info->tree_mod_seq_list)) {
		struct seq_list *elem;

		elem = list_first_entry(&fs_info->tree_mod_seq_list,
					struct seq_list, list);
		seq = elem->seq;
	}
	spin_unlock(&fs_info->tree_mod_seq_lock);

	node = rb_first(&head->ref_root);
	while (node) {
		struct btrfs_delayed_ref_node *ref;

		ref = rb_entry(node, struct btrfs_delayed_ref_node,
			       rb_node);
		/* We can't merge refs that are outside of our seq count */
		if (seq && ref->seq >= seq)
			break;
		if (merge_ref(trans, delayed_refs, head, ref, seq))
			node = rb_first(&head->ref_root);
		else
			node = rb_next(&ref->rb_node);
	}
}

int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
			    struct btrfs_delayed_ref_root *delayed_refs,
			    u64 seq)
{
	struct seq_list *elem;
	int ret = 0;

	spin_lock(&fs_info->tree_mod_seq_lock);
	if (!list_empty(&fs_info->tree_mod_seq_list)) {
		elem = list_first_entry(&fs_info->tree_mod_seq_list,
					struct seq_list, list);
		if (seq >= elem->seq) {
			pr_debug("holding back delayed_ref %#x.%x, lowest is %#x.%x (%p)\n",
				 (u32)(seq >> 32), (u32)seq,
				 (u32)(elem->seq >> 32), (u32)elem->seq,
				 delayed_refs);
			ret = 1;
		}
	}

	spin_unlock(&fs_info->tree_mod_seq_lock);
	return ret;
}

struct btrfs_delayed_ref_head *
btrfs_select_ref_head(struct btrfs_trans_handle *trans)
{
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_delayed_ref_head *head;
	u64 start;
	bool loop = false;

	delayed_refs = &trans->transaction->delayed_refs;

again:
	start = delayed_refs->run_delayed_start;
	head = find_ref_head(&delayed_refs->href_root, start, NULL, 1);
	if (!head && !loop) {
		delayed_refs->run_delayed_start = 0;
		start = 0;
		loop = true;
		head = find_ref_head(&delayed_refs->href_root, start, NULL, 1);
		if (!head)
			return NULL;
	} else if (!head && loop) {
		return NULL;
	}

	while (head->processing) {
		struct rb_node *node;

		node = rb_next(&head->href_node);
		if (!node) {
			if (loop)
				return NULL;
			delayed_refs->run_delayed_start = 0;
			start = 0;
			loop = true;
			goto again;
		}
		head = rb_entry(node, struct btrfs_delayed_ref_head,
				href_node);
	}

	head->processing = 1;
	WARN_ON(delayed_refs->num_heads_ready == 0);
	delayed_refs->num_heads_ready--;
	delayed_refs->run_delayed_start = head->node.bytenr +
		head->node.num_bytes;
	return head;
}

/*
 * helper function to update an extent delayed ref in the
 * rbtree.  existing and update must both have the same
 * bytenr and parent
 *
 * This may free existing if the update cancels out whatever
 * operation it was doing.
 */
static noinline void
update_existing_ref(struct btrfs_trans_handle *trans,
		    struct btrfs_delayed_ref_root *delayed_refs,
		    struct btrfs_delayed_ref_head *head,
		    struct btrfs_delayed_ref_node *existing,
		    struct btrfs_delayed_ref_node *update)
{
	if (update->action != existing->action) {
		/*
		 * this is effectively undoing either an add or a
		 * drop.  We decrement the ref_mod, and if it goes
		 * down to zero we just delete the entry without
		 * every changing the extent allocation tree.
		 */
		existing->ref_mod--;
		if (existing->ref_mod == 0)
			drop_delayed_ref(trans, delayed_refs, head, existing);
		else
			WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
				existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
	} else {
		WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
			existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
		/*
		 * the action on the existing ref matches
		 * the action on the ref we're trying to add.
		 * Bump the ref_mod by one so the backref that
		 * is eventually added/removed has the correct
		 * reference count
		 */
		existing->ref_mod += update->ref_mod;
	}
}

/*
 * helper function to update the accounting in the head ref
 * existing and update must have the same bytenr
 */
static noinline void
update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
			 struct btrfs_delayed_ref_node *update)
{
	struct btrfs_delayed_ref_head *existing_ref;
	struct btrfs_delayed_ref_head *ref;

	existing_ref = btrfs_delayed_node_to_head(existing);
	ref = btrfs_delayed_node_to_head(update);
	BUG_ON(existing_ref->is_data != ref->is_data);

	if (ref->must_insert_reserved) {
		/* if the extent was freed and then
		 * reallocated before the delayed ref
		 * entries were processed, we can end up
		 * with an existing head ref without
		 * the must_insert_reserved flag set.
		 * Set it again here
		 */
		existing_ref->must_insert_reserved = ref->must_insert_reserved;

		/*
		 * update the num_bytes so we make sure the accounting
		 * is done correctly
		 */
		existing->num_bytes = update->num_bytes;

	}

	if (ref->extent_op) {
		if (!existing_ref->extent_op) {
			existing_ref->extent_op = ref->extent_op;
		} else {
			if (ref->extent_op->update_key) {
				memcpy(&existing_ref->extent_op->key,
				       &ref->extent_op->key,
				       sizeof(ref->extent_op->key));
				existing_ref->extent_op->update_key = 1;
			}
			if (ref->extent_op->update_flags) {
				existing_ref->extent_op->flags_to_set |=
					ref->extent_op->flags_to_set;
				existing_ref->extent_op->update_flags = 1;
			}
			btrfs_free_delayed_extent_op(ref->extent_op);
		}
	}
	/*
	 * update the reference mod on the head to reflect this new operation,
	 * only need the lock for this case cause we could be processing it
	 * currently, for refs we just added we know we're a-ok.
	 */
	spin_lock(&existing_ref->lock);
	existing->ref_mod += update->ref_mod;
	spin_unlock(&existing_ref->lock);
}

/*
 * helper function to actually insert a head node into the rbtree.
 * this does all the dirty work in terms of maintaining the correct
 * overall modification count.
 */
static noinline struct btrfs_delayed_ref_head *
add_delayed_ref_head(struct btrfs_fs_info *fs_info,
		     struct btrfs_trans_handle *trans,
		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
		     u64 num_bytes, int action, int is_data)
{
	struct btrfs_delayed_ref_head *existing;
	struct btrfs_delayed_ref_head *head_ref = NULL;
	struct btrfs_delayed_ref_root *delayed_refs;
	int count_mod = 1;
	int must_insert_reserved = 0;

	/*
	 * the head node stores the sum of all the mods, so dropping a ref
	 * should drop the sum in the head node by one.
	 */
	if (action == BTRFS_UPDATE_DELAYED_HEAD)
		count_mod = 0;
	else if (action == BTRFS_DROP_DELAYED_REF)
		count_mod = -1;

	/*
	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update
	 * the reserved accounting when the extent is finally added, or
	 * if a later modification deletes the delayed ref without ever
	 * inserting the extent into the extent allocation tree.
	 * ref->must_insert_reserved is the flag used to record
	 * that accounting mods are required.
	 *
	 * Once we record must_insert_reserved, switch the action to
	 * BTRFS_ADD_DELAYED_REF because other special casing is not required.
	 */
	if (action == BTRFS_ADD_DELAYED_EXTENT)
		must_insert_reserved = 1;
	else
		must_insert_reserved = 0;

	delayed_refs = &trans->transaction->delayed_refs;

	/* first set the basic ref node struct up */
	atomic_set(&ref->refs, 1);
	ref->bytenr = bytenr;
	ref->num_bytes = num_bytes;
	ref->ref_mod = count_mod;
	ref->type  = 0;
	ref->action  = 0;
	ref->is_head = 1;
	ref->in_tree = 1;
	ref->seq = 0;

	head_ref = btrfs_delayed_node_to_head(ref);
	head_ref->must_insert_reserved = must_insert_reserved;
	head_ref->is_data = is_data;
	head_ref->ref_root = RB_ROOT;
	head_ref->processing = 0;

	spin_lock_init(&head_ref->lock);
	mutex_init(&head_ref->mutex);

	trace_add_delayed_ref_head(ref, head_ref, action);

	existing = htree_insert(&delayed_refs->href_root,
				&head_ref->href_node);
	if (existing) {
		update_existing_head_ref(&existing->node, ref);
		/*
		 * we've updated the existing ref, free the newly
		 * allocated ref
		 */
		kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
		head_ref = existing;
	} else {
		delayed_refs->num_heads++;
		delayed_refs->num_heads_ready++;
		atomic_inc(&delayed_refs->num_entries);
		trans->delayed_ref_updates++;
	}
	return head_ref;
}

/*
 * helper to insert a delayed tree ref into the rbtree.
 */
static noinline void
add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
		     struct btrfs_trans_handle *trans,
		     struct btrfs_delayed_ref_head *head_ref,
		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
		     u64 num_bytes, u64 parent, u64 ref_root, int level,
		     int action, int for_cow)
{
	struct btrfs_delayed_ref_node *existing;
	struct btrfs_delayed_tree_ref *full_ref;
	struct btrfs_delayed_ref_root *delayed_refs;
	u64 seq = 0;

	if (action == BTRFS_ADD_DELAYED_EXTENT)
		action = BTRFS_ADD_DELAYED_REF;

	delayed_refs = &trans->transaction->delayed_refs;

	/* first set the basic ref node struct up */
	atomic_set(&ref->refs, 1);
	ref->bytenr = bytenr;
	ref->num_bytes = num_bytes;
	ref->ref_mod = 1;
	ref->action = action;
	ref->is_head = 0;
	ref->in_tree = 1;

	if (need_ref_seq(for_cow, ref_root))
		seq = btrfs_get_tree_mod_seq(fs_info, &trans->delayed_ref_elem);
	ref->seq = seq;

	full_ref = btrfs_delayed_node_to_tree_ref(ref);
	full_ref->parent = parent;
	full_ref->root = ref_root;
	if (parent)
		ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
	else
		ref->type = BTRFS_TREE_BLOCK_REF_KEY;
	full_ref->level = level;

	trace_add_delayed_tree_ref(ref, full_ref, action);

	spin_lock(&head_ref->lock);
	existing = tree_insert(&head_ref->ref_root, &ref->rb_node);
	if (existing) {
		update_existing_ref(trans, delayed_refs, head_ref, existing,
				    ref);
		/*
		 * we've updated the existing ref, free the newly
		 * allocated ref
		 */
		kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
	} else {
		atomic_inc(&delayed_refs->num_entries);
		trans->delayed_ref_updates++;
	}
	spin_unlock(&head_ref->lock);
}

/*
 * helper to insert a delayed data ref into the rbtree.
 */
static noinline void
add_delayed_data_ref(struct btrfs_fs_info *fs_info,
		     struct btrfs_trans_handle *trans,
		     struct btrfs_delayed_ref_head *head_ref,
		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
		     u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
		     u64 offset, int action, int for_cow)
{
	struct btrfs_delayed_ref_node *existing;
	struct btrfs_delayed_data_ref *full_ref;
	struct btrfs_delayed_ref_root *delayed_refs;
	u64 seq = 0;

	if (action == BTRFS_ADD_DELAYED_EXTENT)
		action = BTRFS_ADD_DELAYED_REF;

	delayed_refs = &trans->transaction->delayed_refs;

	/* first set the basic ref node struct up */
	atomic_set(&ref->refs, 1);
	ref->bytenr = bytenr;
	ref->num_bytes = num_bytes;
	ref->ref_mod = 1;
	ref->action = action;
	ref->is_head = 0;
	ref->in_tree = 1;

	if (need_ref_seq(for_cow, ref_root))
		seq = btrfs_get_tree_mod_seq(fs_info, &trans->delayed_ref_elem);
	ref->seq = seq;

	full_ref = btrfs_delayed_node_to_data_ref(ref);
	full_ref->parent = parent;
	full_ref->root = ref_root;
	if (parent)
		ref->type = BTRFS_SHARED_DATA_REF_KEY;
	else
		ref->type = BTRFS_EXTENT_DATA_REF_KEY;

	full_ref->objectid = owner;
	full_ref->offset = offset;

	trace_add_delayed_data_ref(ref, full_ref, action);

	spin_lock(&head_ref->lock);
	existing = tree_insert(&head_ref->ref_root, &ref->rb_node);
	if (existing) {
		update_existing_ref(trans, delayed_refs, head_ref, existing,
				    ref);
		/*
		 * we've updated the existing ref, free the newly
		 * allocated ref
		 */
		kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
	} else {
		atomic_inc(&delayed_refs->num_entries);
		trans->delayed_ref_updates++;
	}
	spin_unlock(&head_ref->lock);
}

/*
 * add a delayed tree ref.  This does all of the accounting required
 * to make sure the delayed ref is eventually processed before this
 * transaction commits.
 */
int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
			       struct btrfs_trans_handle *trans,
			       u64 bytenr, u64 num_bytes, u64 parent,
			       u64 ref_root,  int level, int action,
			       struct btrfs_delayed_extent_op *extent_op,
			       int for_cow)
{
	struct btrfs_delayed_tree_ref *ref;
	struct btrfs_delayed_ref_head *head_ref;
	struct btrfs_delayed_ref_root *delayed_refs;

	BUG_ON(extent_op && extent_op->is_data);
	ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
	if (!ref)
		return -ENOMEM;

	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
	if (!head_ref) {
		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
		return -ENOMEM;
	}

	head_ref->extent_op = extent_op;

	delayed_refs = &trans->transaction->delayed_refs;
	spin_lock(&delayed_refs->lock);

	/*
	 * insert both the head node and the new ref without dropping
	 * the spin lock
	 */
	head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node,
					bytenr, num_bytes, action, 0);

	add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
				   num_bytes, parent, ref_root, level, action,
				   for_cow);
	spin_unlock(&delayed_refs->lock);
	if (need_ref_seq(for_cow, ref_root))
		btrfs_qgroup_record_ref(trans, &ref->node, extent_op);

	return 0;
}

/*
 * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
 */
int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
			       struct btrfs_trans_handle *trans,
			       u64 bytenr, u64 num_bytes,
			       u64 parent, u64 ref_root,
			       u64 owner, u64 offset, int action,
			       struct btrfs_delayed_extent_op *extent_op,
			       int for_cow)
{
	struct btrfs_delayed_data_ref *ref;
	struct btrfs_delayed_ref_head *head_ref;
	struct btrfs_delayed_ref_root *delayed_refs;

	BUG_ON(extent_op && !extent_op->is_data);
	ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
	if (!ref)
		return -ENOMEM;

	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
	if (!head_ref) {
		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
		return -ENOMEM;
	}

	head_ref->extent_op = extent_op;

	delayed_refs = &trans->transaction->delayed_refs;
	spin_lock(&delayed_refs->lock);

	/*
	 * insert both the head node and the new ref without dropping
	 * the spin lock
	 */
	head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node,
					bytenr, num_bytes, action, 1);

	add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
				   num_bytes, parent, ref_root, owner, offset,
				   action, for_cow);
	spin_unlock(&delayed_refs->lock);
	if (need_ref_seq(for_cow, ref_root))
		btrfs_qgroup_record_ref(trans, &ref->node, extent_op);

	return 0;
}

int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
				struct btrfs_trans_handle *trans,
				u64 bytenr, u64 num_bytes,
				struct btrfs_delayed_extent_op *extent_op)
{
	struct btrfs_delayed_ref_head *head_ref;
	struct btrfs_delayed_ref_root *delayed_refs;

	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
	if (!head_ref)
		return -ENOMEM;

	head_ref->extent_op = extent_op;

	delayed_refs = &trans->transaction->delayed_refs;
	spin_lock(&delayed_refs->lock);

	add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
				   num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
				   extent_op->is_data);

	spin_unlock(&delayed_refs->lock);
	return 0;
}

/*
 * this does a simple search for the head node for a given extent.
 * It must be called with the delayed ref spinlock held, and it returns
 * the head node if any where found, or NULL if not.
 */
struct btrfs_delayed_ref_head *
btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
{
	struct btrfs_delayed_ref_root *delayed_refs;

	delayed_refs = &trans->transaction->delayed_refs;
	return find_ref_head(&delayed_refs->href_root, bytenr, NULL, 0);
}

void btrfs_delayed_ref_exit(void)
{
	if (btrfs_delayed_ref_head_cachep)
		kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
	if (btrfs_delayed_tree_ref_cachep)
		kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
	if (btrfs_delayed_data_ref_cachep)
		kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
	if (btrfs_delayed_extent_op_cachep)
		kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
}

int btrfs_delayed_ref_init(void)
{
	btrfs_delayed_ref_head_cachep = kmem_cache_create(
				"btrfs_delayed_ref_head",
				sizeof(struct btrfs_delayed_ref_head), 0,
				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
	if (!btrfs_delayed_ref_head_cachep)
		goto fail;

	btrfs_delayed_tree_ref_cachep = kmem_cache_create(
				"btrfs_delayed_tree_ref",
				sizeof(struct btrfs_delayed_tree_ref), 0,
				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
	if (!btrfs_delayed_tree_ref_cachep)
		goto fail;

	btrfs_delayed_data_ref_cachep = kmem_cache_create(
				"btrfs_delayed_data_ref",
				sizeof(struct btrfs_delayed_data_ref), 0,
				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
	if (!btrfs_delayed_data_ref_cachep)
		goto fail;

	btrfs_delayed_extent_op_cachep = kmem_cache_create(
				"btrfs_delayed_extent_op",
				sizeof(struct btrfs_delayed_extent_op), 0,
				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
	if (!btrfs_delayed_extent_op_cachep)
		goto fail;

	return 0;
fail:
	btrfs_delayed_ref_exit();
	return -ENOMEM;
}