aboutsummaryrefslogtreecommitdiff
path: root/sys/contrib/openzfs/module/zfs/dnode_sync.c
blob: dd37e3af7ed5aa9ca72be19b3bfe2465ac310c1b (plain) (blame)
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
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

/*
 * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
 * Copyright (c) 2012, 2020 by Delphix. All rights reserved.
 * Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
 * Copyright 2020 Oxide Computer Company
 */

#include <sys/zfs_context.h>
#include <sys/dbuf.h>
#include <sys/dnode.h>
#include <sys/dmu.h>
#include <sys/dmu_tx.h>
#include <sys/dmu_objset.h>
#include <sys/dmu_recv.h>
#include <sys/dsl_dataset.h>
#include <sys/spa.h>
#include <sys/range_tree.h>
#include <sys/zfeature.h>

static void
dnode_increase_indirection(dnode_t *dn, dmu_tx_t *tx)
{
	dmu_buf_impl_t *db;
	int txgoff = tx->tx_txg & TXG_MASK;
	int nblkptr = dn->dn_phys->dn_nblkptr;
	int old_toplvl = dn->dn_phys->dn_nlevels - 1;
	int new_level = dn->dn_next_nlevels[txgoff];
	int i;

	rw_enter(&dn->dn_struct_rwlock, RW_WRITER);

	/* this dnode can't be paged out because it's dirty */
	ASSERT(dn->dn_phys->dn_type != DMU_OT_NONE);
	ASSERT(new_level > 1 && dn->dn_phys->dn_nlevels > 0);

	db = dbuf_hold_level(dn, dn->dn_phys->dn_nlevels, 0, FTAG);
	ASSERT(db != NULL);

	dn->dn_phys->dn_nlevels = new_level;
	dprintf("os=%p obj=%llu, increase to %d\n", dn->dn_objset,
	    (u_longlong_t)dn->dn_object, dn->dn_phys->dn_nlevels);

	/*
	 * Lock ordering requires that we hold the children's db_mutexes (by
	 * calling dbuf_find()) before holding the parent's db_rwlock.  The lock
	 * order is imposed by dbuf_read's steps of "grab the lock to protect
	 * db_parent, get db_parent, hold db_parent's db_rwlock".
	 */
	dmu_buf_impl_t *children[DN_MAX_NBLKPTR];
	ASSERT3U(nblkptr, <=, DN_MAX_NBLKPTR);
	for (i = 0; i < nblkptr; i++) {
		children[i] =
		    dbuf_find(dn->dn_objset, dn->dn_object, old_toplvl, i);
	}

	/* transfer dnode's block pointers to new indirect block */
	(void) dbuf_read(db, NULL, DB_RF_MUST_SUCCEED|DB_RF_HAVESTRUCT);
	if (dn->dn_dbuf != NULL)
		rw_enter(&dn->dn_dbuf->db_rwlock, RW_WRITER);
	rw_enter(&db->db_rwlock, RW_WRITER);
	ASSERT(db->db.db_data);
	ASSERT(arc_released(db->db_buf));
	ASSERT3U(sizeof (blkptr_t) * nblkptr, <=, db->db.db_size);
	bcopy(dn->dn_phys->dn_blkptr, db->db.db_data,
	    sizeof (blkptr_t) * nblkptr);
	arc_buf_freeze(db->db_buf);

	/* set dbuf's parent pointers to new indirect buf */
	for (i = 0; i < nblkptr; i++) {
		dmu_buf_impl_t *child = children[i];

		if (child == NULL)
			continue;
#ifdef	ZFS_DEBUG
		DB_DNODE_ENTER(child);
		ASSERT3P(DB_DNODE(child), ==, dn);
		DB_DNODE_EXIT(child);
#endif	/* DEBUG */
		if (child->db_parent && child->db_parent != dn->dn_dbuf) {
			ASSERT(child->db_parent->db_level == db->db_level);
			ASSERT(child->db_blkptr !=
			    &dn->dn_phys->dn_blkptr[child->db_blkid]);
			mutex_exit(&child->db_mtx);
			continue;
		}
		ASSERT(child->db_parent == NULL ||
		    child->db_parent == dn->dn_dbuf);

		child->db_parent = db;
		dbuf_add_ref(db, child);
		if (db->db.db_data)
			child->db_blkptr = (blkptr_t *)db->db.db_data + i;
		else
			child->db_blkptr = NULL;
		dprintf_dbuf_bp(child, child->db_blkptr,
		    "changed db_blkptr to new indirect %s", "");

		mutex_exit(&child->db_mtx);
	}

	bzero(dn->dn_phys->dn_blkptr, sizeof (blkptr_t) * nblkptr);

	rw_exit(&db->db_rwlock);
	if (dn->dn_dbuf != NULL)
		rw_exit(&dn->dn_dbuf->db_rwlock);

	dbuf_rele(db, FTAG);

	rw_exit(&dn->dn_struct_rwlock);
}

static void
free_blocks(dnode_t *dn, blkptr_t *bp, int num, dmu_tx_t *tx)
{
	dsl_dataset_t *ds = dn->dn_objset->os_dsl_dataset;
	uint64_t bytesfreed = 0;

	dprintf("ds=%p obj=%llx num=%d\n", ds, (u_longlong_t)dn->dn_object,
	    num);

	for (int i = 0; i < num; i++, bp++) {
		if (BP_IS_HOLE(bp))
			continue;

		bytesfreed += dsl_dataset_block_kill(ds, bp, tx, B_FALSE);
		ASSERT3U(bytesfreed, <=, DN_USED_BYTES(dn->dn_phys));

		/*
		 * Save some useful information on the holes being
		 * punched, including logical size, type, and indirection
		 * level. Retaining birth time enables detection of when
		 * holes are punched for reducing the number of free
		 * records transmitted during a zfs send.
		 */

		uint64_t lsize = BP_GET_LSIZE(bp);
		dmu_object_type_t type = BP_GET_TYPE(bp);
		uint64_t lvl = BP_GET_LEVEL(bp);

		bzero(bp, sizeof (blkptr_t));

		if (spa_feature_is_active(dn->dn_objset->os_spa,
		    SPA_FEATURE_HOLE_BIRTH)) {
			BP_SET_LSIZE(bp, lsize);
			BP_SET_TYPE(bp, type);
			BP_SET_LEVEL(bp, lvl);
			BP_SET_BIRTH(bp, dmu_tx_get_txg(tx), 0);
		}
	}
	dnode_diduse_space(dn, -bytesfreed);
}

#ifdef ZFS_DEBUG
static void
free_verify(dmu_buf_impl_t *db, uint64_t start, uint64_t end, dmu_tx_t *tx)
{
	int off, num;
	int i, err, epbs;
	uint64_t txg = tx->tx_txg;
	dnode_t *dn;

	DB_DNODE_ENTER(db);
	dn = DB_DNODE(db);
	epbs = dn->dn_phys->dn_indblkshift - SPA_BLKPTRSHIFT;
	off = start - (db->db_blkid * 1<<epbs);
	num = end - start + 1;

	ASSERT3U(off, >=, 0);
	ASSERT3U(num, >=, 0);
	ASSERT3U(db->db_level, >, 0);
	ASSERT3U(db->db.db_size, ==, 1 << dn->dn_phys->dn_indblkshift);
	ASSERT3U(off+num, <=, db->db.db_size >> SPA_BLKPTRSHIFT);
	ASSERT(db->db_blkptr != NULL);

	for (i = off; i < off+num; i++) {
		uint64_t *buf;
		dmu_buf_impl_t *child;
		dbuf_dirty_record_t *dr;
		int j;

		ASSERT(db->db_level == 1);

		rw_enter(&dn->dn_struct_rwlock, RW_READER);
		err = dbuf_hold_impl(dn, db->db_level - 1,
		    (db->db_blkid << epbs) + i, TRUE, FALSE, FTAG, &child);
		rw_exit(&dn->dn_struct_rwlock);
		if (err == ENOENT)
			continue;
		ASSERT(err == 0);
		ASSERT(child->db_level == 0);
		dr = dbuf_find_dirty_eq(child, txg);

		/* data_old better be zeroed */
		if (dr) {
			buf = dr->dt.dl.dr_data->b_data;
			for (j = 0; j < child->db.db_size >> 3; j++) {
				if (buf[j] != 0) {
					panic("freed data not zero: "
					    "child=%p i=%d off=%d num=%d\n",
					    (void *)child, i, off, num);
				}
			}
		}

		/*
		 * db_data better be zeroed unless it's dirty in a
		 * future txg.
		 */
		mutex_enter(&child->db_mtx);
		buf = child->db.db_data;
		if (buf != NULL && child->db_state != DB_FILL &&
		    list_is_empty(&child->db_dirty_records)) {
			for (j = 0; j < child->db.db_size >> 3; j++) {
				if (buf[j] != 0) {
					panic("freed data not zero: "
					    "child=%p i=%d off=%d num=%d\n",
					    (void *)child, i, off, num);
				}
			}
		}
		mutex_exit(&child->db_mtx);

		dbuf_rele(child, FTAG);
	}
	DB_DNODE_EXIT(db);
}
#endif

/*
 * We don't usually free the indirect blocks here.  If in one txg we have a
 * free_range and a write to the same indirect block, it's important that we
 * preserve the hole's birth times. Therefore, we don't free any any indirect
 * blocks in free_children().  If an indirect block happens to turn into all
 * holes, it will be freed by dbuf_write_children_ready, which happens at a
 * point in the syncing process where we know for certain the contents of the
 * indirect block.
 *
 * However, if we're freeing a dnode, its space accounting must go to zero
 * before we actually try to free the dnode, or we will trip an assertion. In
 * addition, we know the case described above cannot occur, because the dnode is
 * being freed.  Therefore, we free the indirect blocks immediately in that
 * case.
 */
static void
free_children(dmu_buf_impl_t *db, uint64_t blkid, uint64_t nblks,
    boolean_t free_indirects, dmu_tx_t *tx)
{
	dnode_t *dn;
	blkptr_t *bp;
	dmu_buf_impl_t *subdb;
	uint64_t start, end, dbstart, dbend;
	unsigned int epbs, shift, i;

	/*
	 * There is a small possibility that this block will not be cached:
	 *   1 - if level > 1 and there are no children with level <= 1
	 *   2 - if this block was evicted since we read it from
	 *	 dmu_tx_hold_free().
	 */
	if (db->db_state != DB_CACHED)
		(void) dbuf_read(db, NULL, DB_RF_MUST_SUCCEED);

	/*
	 * If we modify this indirect block, and we are not freeing the
	 * dnode (!free_indirects), then this indirect block needs to get
	 * written to disk by dbuf_write().  If it is dirty, we know it will
	 * be written (otherwise, we would have incorrect on-disk state
	 * because the space would be freed but still referenced by the BP
	 * in this indirect block).  Therefore we VERIFY that it is
	 * dirty.
	 *
	 * Our VERIFY covers some cases that do not actually have to be
	 * dirty, but the open-context code happens to dirty.  E.g. if the
	 * blocks we are freeing are all holes, because in that case, we
	 * are only freeing part of this indirect block, so it is an
	 * ancestor of the first or last block to be freed.  The first and
	 * last L1 indirect blocks are always dirtied by dnode_free_range().
	 */
	db_lock_type_t dblt = dmu_buf_lock_parent(db, RW_READER, FTAG);
	VERIFY(BP_GET_FILL(db->db_blkptr) == 0 || db->db_dirtycnt > 0);
	dmu_buf_unlock_parent(db, dblt, FTAG);

	dbuf_release_bp(db);
	bp = db->db.db_data;

	DB_DNODE_ENTER(db);
	dn = DB_DNODE(db);
	epbs = dn->dn_phys->dn_indblkshift - SPA_BLKPTRSHIFT;
	ASSERT3U(epbs, <, 31);
	shift = (db->db_level - 1) * epbs;
	dbstart = db->db_blkid << epbs;
	start = blkid >> shift;
	if (dbstart < start) {
		bp += start - dbstart;
	} else {
		start = dbstart;
	}
	dbend = ((db->db_blkid + 1) << epbs) - 1;
	end = (blkid + nblks - 1) >> shift;
	if (dbend <= end)
		end = dbend;

	ASSERT3U(start, <=, end);

	if (db->db_level == 1) {
		FREE_VERIFY(db, start, end, tx);
		rw_enter(&db->db_rwlock, RW_WRITER);
		free_blocks(dn, bp, end - start + 1, tx);
		rw_exit(&db->db_rwlock);
	} else {
		for (uint64_t id = start; id <= end; id++, bp++) {
			if (BP_IS_HOLE(bp))
				continue;
			rw_enter(&dn->dn_struct_rwlock, RW_READER);
			VERIFY0(dbuf_hold_impl(dn, db->db_level - 1,
			    id, TRUE, FALSE, FTAG, &subdb));
			rw_exit(&dn->dn_struct_rwlock);
			ASSERT3P(bp, ==, subdb->db_blkptr);

			free_children(subdb, blkid, nblks, free_indirects, tx);
			dbuf_rele(subdb, FTAG);
		}
	}

	if (free_indirects) {
		rw_enter(&db->db_rwlock, RW_WRITER);
		for (i = 0, bp = db->db.db_data; i < 1 << epbs; i++, bp++)
			ASSERT(BP_IS_HOLE(bp));
		bzero(db->db.db_data, db->db.db_size);
		free_blocks(dn, db->db_blkptr, 1, tx);
		rw_exit(&db->db_rwlock);
	}

	DB_DNODE_EXIT(db);
	arc_buf_freeze(db->db_buf);
}

/*
 * Traverse the indicated range of the provided file
 * and "free" all the blocks contained there.
 */
static void
dnode_sync_free_range_impl(dnode_t *dn, uint64_t blkid, uint64_t nblks,
    boolean_t free_indirects, dmu_tx_t *tx)
{
	blkptr_t *bp = dn->dn_phys->dn_blkptr;
	int dnlevel = dn->dn_phys->dn_nlevels;
	boolean_t trunc = B_FALSE;

	if (blkid > dn->dn_phys->dn_maxblkid)
		return;

	ASSERT(dn->dn_phys->dn_maxblkid < UINT64_MAX);
	if (blkid + nblks > dn->dn_phys->dn_maxblkid) {
		nblks = dn->dn_phys->dn_maxblkid - blkid + 1;
		trunc = B_TRUE;
	}

	/* There are no indirect blocks in the object */
	if (dnlevel == 1) {
		if (blkid >= dn->dn_phys->dn_nblkptr) {
			/* this range was never made persistent */
			return;
		}
		ASSERT3U(blkid + nblks, <=, dn->dn_phys->dn_nblkptr);
		free_blocks(dn, bp + blkid, nblks, tx);
	} else {
		int shift = (dnlevel - 1) *
		    (dn->dn_phys->dn_indblkshift - SPA_BLKPTRSHIFT);
		int start = blkid >> shift;
		int end = (blkid + nblks - 1) >> shift;
		dmu_buf_impl_t *db;

		ASSERT(start < dn->dn_phys->dn_nblkptr);
		bp += start;
		for (int i = start; i <= end; i++, bp++) {
			if (BP_IS_HOLE(bp))
				continue;
			rw_enter(&dn->dn_struct_rwlock, RW_READER);
			VERIFY0(dbuf_hold_impl(dn, dnlevel - 1, i,
			    TRUE, FALSE, FTAG, &db));
			rw_exit(&dn->dn_struct_rwlock);
			free_children(db, blkid, nblks, free_indirects, tx);
			dbuf_rele(db, FTAG);
		}
	}

	/*
	 * Do not truncate the maxblkid if we are performing a raw
	 * receive. The raw receive sets the maxblkid manually and
	 * must not be overridden. Usually, the last DRR_FREE record
	 * will be at the maxblkid, because the source system sets
	 * the maxblkid when truncating. However, if the last block
	 * was freed by overwriting with zeros and being compressed
	 * away to a hole, the source system will generate a DRR_FREE
	 * record while leaving the maxblkid after the end of that
	 * record. In this case we need to leave the maxblkid as
	 * indicated in the DRR_OBJECT record, so that it matches the
	 * source system, ensuring that the cryptographic hashes will
	 * match.
	 */
	if (trunc && !dn->dn_objset->os_raw_receive) {
		uint64_t off __maybe_unused;
		dn->dn_phys->dn_maxblkid = blkid == 0 ? 0 : blkid - 1;

		off = (dn->dn_phys->dn_maxblkid + 1) *
		    (dn->dn_phys->dn_datablkszsec << SPA_MINBLOCKSHIFT);
		ASSERT(off < dn->dn_phys->dn_maxblkid ||
		    dn->dn_phys->dn_maxblkid == 0 ||
		    dnode_next_offset(dn, 0, &off, 1, 1, 0) != 0);
	}
}

typedef struct dnode_sync_free_range_arg {
	dnode_t *dsfra_dnode;
	dmu_tx_t *dsfra_tx;
	boolean_t dsfra_free_indirects;
} dnode_sync_free_range_arg_t;

static void
dnode_sync_free_range(void *arg, uint64_t blkid, uint64_t nblks)
{
	dnode_sync_free_range_arg_t *dsfra = arg;
	dnode_t *dn = dsfra->dsfra_dnode;

	mutex_exit(&dn->dn_mtx);
	dnode_sync_free_range_impl(dn, blkid, nblks,
	    dsfra->dsfra_free_indirects, dsfra->dsfra_tx);
	mutex_enter(&dn->dn_mtx);
}

/*
 * Try to kick all the dnode's dbufs out of the cache...
 */
void
dnode_evict_dbufs(dnode_t *dn)
{
	dmu_buf_impl_t *db_marker;
	dmu_buf_impl_t *db, *db_next;

	db_marker = kmem_alloc(sizeof (dmu_buf_impl_t), KM_SLEEP);

	mutex_enter(&dn->dn_dbufs_mtx);
	for (db = avl_first(&dn->dn_dbufs); db != NULL; db = db_next) {

#ifdef	ZFS_DEBUG
		DB_DNODE_ENTER(db);
		ASSERT3P(DB_DNODE(db), ==, dn);
		DB_DNODE_EXIT(db);
#endif	/* DEBUG */

		mutex_enter(&db->db_mtx);
		if (db->db_state != DB_EVICTING &&
		    zfs_refcount_is_zero(&db->db_holds)) {
			db_marker->db_level = db->db_level;
			db_marker->db_blkid = db->db_blkid;
			db_marker->db_state = DB_SEARCH;
			avl_insert_here(&dn->dn_dbufs, db_marker, db,
			    AVL_BEFORE);

			/*
			 * We need to use the "marker" dbuf rather than
			 * simply getting the next dbuf, because
			 * dbuf_destroy() may actually remove multiple dbufs.
			 * It can call itself recursively on the parent dbuf,
			 * which may also be removed from dn_dbufs.  The code
			 * flow would look like:
			 *
			 * dbuf_destroy():
			 *   dnode_rele_and_unlock(parent_dbuf, evicting=TRUE):
			 *	if (!cacheable || pending_evict)
			 *	  dbuf_destroy()
			 */
			dbuf_destroy(db);

			db_next = AVL_NEXT(&dn->dn_dbufs, db_marker);
			avl_remove(&dn->dn_dbufs, db_marker);
		} else {
			db->db_pending_evict = TRUE;
			mutex_exit(&db->db_mtx);
			db_next = AVL_NEXT(&dn->dn_dbufs, db);
		}
	}
	mutex_exit(&dn->dn_dbufs_mtx);

	kmem_free(db_marker, sizeof (dmu_buf_impl_t));

	dnode_evict_bonus(dn);
}

void
dnode_evict_bonus(dnode_t *dn)
{
	rw_enter(&dn->dn_struct_rwlock, RW_WRITER);
	if (dn->dn_bonus != NULL) {
		if (zfs_refcount_is_zero(&dn->dn_bonus->db_holds)) {
			mutex_enter(&dn->dn_bonus->db_mtx);
			dbuf_destroy(dn->dn_bonus);
			dn->dn_bonus = NULL;
		} else {
			dn->dn_bonus->db_pending_evict = TRUE;
		}
	}
	rw_exit(&dn->dn_struct_rwlock);
}

static void
dnode_undirty_dbufs(list_t *list)
{
	dbuf_dirty_record_t *dr;

	while ((dr = list_head(list))) {
		dmu_buf_impl_t *db = dr->dr_dbuf;
		uint64_t txg = dr->dr_txg;

		if (db->db_level != 0)
			dnode_undirty_dbufs(&dr->dt.di.dr_children);

		mutex_enter(&db->db_mtx);
		/* XXX - use dbuf_undirty()? */
		list_remove(list, dr);
		ASSERT(list_head(&db->db_dirty_records) == dr);
		list_remove_head(&db->db_dirty_records);
		ASSERT(list_is_empty(&db->db_dirty_records));
		db->db_dirtycnt -= 1;
		if (db->db_level == 0) {
			ASSERT(db->db_blkid == DMU_BONUS_BLKID ||
			    dr->dt.dl.dr_data == db->db_buf);
			dbuf_unoverride(dr);
		} else {
			mutex_destroy(&dr->dt.di.dr_mtx);
			list_destroy(&dr->dt.di.dr_children);
		}
		kmem_free(dr, sizeof (dbuf_dirty_record_t));
		dbuf_rele_and_unlock(db, (void *)(uintptr_t)txg, B_FALSE);
	}
}

static void
dnode_sync_free(dnode_t *dn, dmu_tx_t *tx)
{
	int txgoff = tx->tx_txg & TXG_MASK;

	ASSERT(dmu_tx_is_syncing(tx));

	/*
	 * Our contents should have been freed in dnode_sync() by the
	 * free range record inserted by the caller of dnode_free().
	 */
	ASSERT0(DN_USED_BYTES(dn->dn_phys));
	ASSERT(BP_IS_HOLE(dn->dn_phys->dn_blkptr));

	dnode_undirty_dbufs(&dn->dn_dirty_records[txgoff]);
	dnode_evict_dbufs(dn);

	/*
	 * XXX - It would be nice to assert this, but we may still
	 * have residual holds from async evictions from the arc...
	 *
	 * zfs_obj_to_path() also depends on this being
	 * commented out.
	 *
	 * ASSERT3U(zfs_refcount_count(&dn->dn_holds), ==, 1);
	 */

	/* Undirty next bits */
	dn->dn_next_nlevels[txgoff] = 0;
	dn->dn_next_indblkshift[txgoff] = 0;
	dn->dn_next_blksz[txgoff] = 0;
	dn->dn_next_maxblkid[txgoff] = 0;

	/* ASSERT(blkptrs are zero); */
	ASSERT(dn->dn_phys->dn_type != DMU_OT_NONE);
	ASSERT(dn->dn_type != DMU_OT_NONE);

	ASSERT(dn->dn_free_txg > 0);
	if (dn->dn_allocated_txg != dn->dn_free_txg)
		dmu_buf_will_dirty(&dn->dn_dbuf->db, tx);
	bzero(dn->dn_phys, sizeof (dnode_phys_t) * dn->dn_num_slots);
	dnode_free_interior_slots(dn);

	mutex_enter(&dn->dn_mtx);
	dn->dn_type = DMU_OT_NONE;
	dn->dn_maxblkid = 0;
	dn->dn_allocated_txg = 0;
	dn->dn_free_txg = 0;
	dn->dn_have_spill = B_FALSE;
	dn->dn_num_slots = 1;
	mutex_exit(&dn->dn_mtx);

	ASSERT(dn->dn_object != DMU_META_DNODE_OBJECT);

	dnode_rele(dn, (void *)(uintptr_t)tx->tx_txg);
	/*
	 * Now that we've released our hold, the dnode may
	 * be evicted, so we mustn't access it.
	 */
}

/*
 * Write out the dnode's dirty buffers.
 */
void
dnode_sync(dnode_t *dn, dmu_tx_t *tx)
{
	objset_t *os = dn->dn_objset;
	dnode_phys_t *dnp = dn->dn_phys;
	int txgoff = tx->tx_txg & TXG_MASK;
	list_t *list = &dn->dn_dirty_records[txgoff];
	static const dnode_phys_t zerodn __maybe_unused = { 0 };
	boolean_t kill_spill = B_FALSE;

	ASSERT(dmu_tx_is_syncing(tx));
	ASSERT(dnp->dn_type != DMU_OT_NONE || dn->dn_allocated_txg);
	ASSERT(dnp->dn_type != DMU_OT_NONE ||
	    bcmp(dnp, &zerodn, DNODE_MIN_SIZE) == 0);
	DNODE_VERIFY(dn);

	ASSERT(dn->dn_dbuf == NULL || arc_released(dn->dn_dbuf->db_buf));

	/*
	 * Do user accounting if it is enabled and this is not
	 * an encrypted receive.
	 */
	if (dmu_objset_userused_enabled(os) &&
	    !DMU_OBJECT_IS_SPECIAL(dn->dn_object) &&
	    (!os->os_encrypted || !dmu_objset_is_receiving(os))) {
		mutex_enter(&dn->dn_mtx);
		dn->dn_oldused = DN_USED_BYTES(dn->dn_phys);
		dn->dn_oldflags = dn->dn_phys->dn_flags;
		dn->dn_phys->dn_flags |= DNODE_FLAG_USERUSED_ACCOUNTED;
		if (dmu_objset_userobjused_enabled(dn->dn_objset))
			dn->dn_phys->dn_flags |=
			    DNODE_FLAG_USEROBJUSED_ACCOUNTED;
		mutex_exit(&dn->dn_mtx);
		dmu_objset_userquota_get_ids(dn, B_FALSE, tx);
	} else {
		/* Once we account for it, we should always account for it */
		ASSERT(!(dn->dn_phys->dn_flags &
		    DNODE_FLAG_USERUSED_ACCOUNTED));
		ASSERT(!(dn->dn_phys->dn_flags &
		    DNODE_FLAG_USEROBJUSED_ACCOUNTED));
	}

	mutex_enter(&dn->dn_mtx);
	if (dn->dn_allocated_txg == tx->tx_txg) {
		/* The dnode is newly allocated or reallocated */
		if (dnp->dn_type == DMU_OT_NONE) {
			/* this is a first alloc, not a realloc */
			dnp->dn_nlevels = 1;
			dnp->dn_nblkptr = dn->dn_nblkptr;
		}

		dnp->dn_type = dn->dn_type;
		dnp->dn_bonustype = dn->dn_bonustype;
		dnp->dn_bonuslen = dn->dn_bonuslen;
	}

	dnp->dn_extra_slots = dn->dn_num_slots - 1;

	ASSERT(dnp->dn_nlevels > 1 ||
	    BP_IS_HOLE(&dnp->dn_blkptr[0]) ||
	    BP_IS_EMBEDDED(&dnp->dn_blkptr[0]) ||
	    BP_GET_LSIZE(&dnp->dn_blkptr[0]) ==
	    dnp->dn_datablkszsec << SPA_MINBLOCKSHIFT);
	ASSERT(dnp->dn_nlevels < 2 ||
	    BP_IS_HOLE(&dnp->dn_blkptr[0]) ||
	    BP_GET_LSIZE(&dnp->dn_blkptr[0]) == 1 << dnp->dn_indblkshift);

	if (dn->dn_next_type[txgoff] != 0) {
		dnp->dn_type = dn->dn_type;
		dn->dn_next_type[txgoff] = 0;
	}

	if (dn->dn_next_blksz[txgoff] != 0) {
		ASSERT(P2PHASE(dn->dn_next_blksz[txgoff],
		    SPA_MINBLOCKSIZE) == 0);
		ASSERT(BP_IS_HOLE(&dnp->dn_blkptr[0]) ||
		    dn->dn_maxblkid == 0 || list_head(list) != NULL ||
		    dn->dn_next_blksz[txgoff] >> SPA_MINBLOCKSHIFT ==
		    dnp->dn_datablkszsec ||
		    !range_tree_is_empty(dn->dn_free_ranges[txgoff]));
		dnp->dn_datablkszsec =
		    dn->dn_next_blksz[txgoff] >> SPA_MINBLOCKSHIFT;
		dn->dn_next_blksz[txgoff] = 0;
	}

	if (dn->dn_next_bonuslen[txgoff] != 0) {
		if (dn->dn_next_bonuslen[txgoff] == DN_ZERO_BONUSLEN)
			dnp->dn_bonuslen = 0;
		else
			dnp->dn_bonuslen = dn->dn_next_bonuslen[txgoff];
		ASSERT(dnp->dn_bonuslen <=
		    DN_SLOTS_TO_BONUSLEN(dnp->dn_extra_slots + 1));
		dn->dn_next_bonuslen[txgoff] = 0;
	}

	if (dn->dn_next_bonustype[txgoff] != 0) {
		ASSERT(DMU_OT_IS_VALID(dn->dn_next_bonustype[txgoff]));
		dnp->dn_bonustype = dn->dn_next_bonustype[txgoff];
		dn->dn_next_bonustype[txgoff] = 0;
	}

	boolean_t freeing_dnode = dn->dn_free_txg > 0 &&
	    dn->dn_free_txg <= tx->tx_txg;

	/*
	 * Remove the spill block if we have been explicitly asked to
	 * remove it, or if the object is being removed.
	 */
	if (dn->dn_rm_spillblk[txgoff] || freeing_dnode) {
		if (dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR)
			kill_spill = B_TRUE;
		dn->dn_rm_spillblk[txgoff] = 0;
	}

	if (dn->dn_next_indblkshift[txgoff] != 0) {
		ASSERT(dnp->dn_nlevels == 1);
		dnp->dn_indblkshift = dn->dn_next_indblkshift[txgoff];
		dn->dn_next_indblkshift[txgoff] = 0;
	}

	/*
	 * Just take the live (open-context) values for checksum and compress.
	 * Strictly speaking it's a future leak, but nothing bad happens if we
	 * start using the new checksum or compress algorithm a little early.
	 */
	dnp->dn_checksum = dn->dn_checksum;
	dnp->dn_compress = dn->dn_compress;

	mutex_exit(&dn->dn_mtx);

	if (kill_spill) {
		free_blocks(dn, DN_SPILL_BLKPTR(dn->dn_phys), 1, tx);
		mutex_enter(&dn->dn_mtx);
		dnp->dn_flags &= ~DNODE_FLAG_SPILL_BLKPTR;
		mutex_exit(&dn->dn_mtx);
	}

	/* process all the "freed" ranges in the file */
	if (dn->dn_free_ranges[txgoff] != NULL) {
		dnode_sync_free_range_arg_t dsfra;
		dsfra.dsfra_dnode = dn;
		dsfra.dsfra_tx = tx;
		dsfra.dsfra_free_indirects = freeing_dnode;
		mutex_enter(&dn->dn_mtx);
		if (freeing_dnode) {
			ASSERT(range_tree_contains(dn->dn_free_ranges[txgoff],
			    0, dn->dn_maxblkid + 1));
		}
		/*
		 * Because dnode_sync_free_range() must drop dn_mtx during its
		 * processing, using it as a callback to range_tree_vacate() is
		 * not safe.  No other operations (besides destroy) are allowed
		 * once range_tree_vacate() has begun, and dropping dn_mtx
		 * would leave a window open for another thread to observe that
		 * invalid (and unsafe) state.
		 */
		range_tree_walk(dn->dn_free_ranges[txgoff],
		    dnode_sync_free_range, &dsfra);
		range_tree_vacate(dn->dn_free_ranges[txgoff], NULL, NULL);
		range_tree_destroy(dn->dn_free_ranges[txgoff]);
		dn->dn_free_ranges[txgoff] = NULL;
		mutex_exit(&dn->dn_mtx);
	}

	if (freeing_dnode) {
		dn->dn_objset->os_freed_dnodes++;
		dnode_sync_free(dn, tx);
		return;
	}

	if (dn->dn_num_slots > DNODE_MIN_SLOTS) {
		dsl_dataset_t *ds = dn->dn_objset->os_dsl_dataset;
		mutex_enter(&ds->ds_lock);
		ds->ds_feature_activation[SPA_FEATURE_LARGE_DNODE] =
		    (void *)B_TRUE;
		mutex_exit(&ds->ds_lock);
	}

	if (dn->dn_next_nlevels[txgoff]) {
		dnode_increase_indirection(dn, tx);
		dn->dn_next_nlevels[txgoff] = 0;
	}

	/*
	 * This must be done after dnode_sync_free_range()
	 * and dnode_increase_indirection(). See dnode_new_blkid()
	 * for an explanation of the high bit being set.
	 */
	if (dn->dn_next_maxblkid[txgoff]) {
		mutex_enter(&dn->dn_mtx);
		dnp->dn_maxblkid =
		    dn->dn_next_maxblkid[txgoff] & ~DMU_NEXT_MAXBLKID_SET;
		dn->dn_next_maxblkid[txgoff] = 0;
		mutex_exit(&dn->dn_mtx);
	}

	if (dn->dn_next_nblkptr[txgoff]) {
		/* this should only happen on a realloc */
		ASSERT(dn->dn_allocated_txg == tx->tx_txg);
		if (dn->dn_next_nblkptr[txgoff] > dnp->dn_nblkptr) {
			/* zero the new blkptrs we are gaining */
			bzero(dnp->dn_blkptr + dnp->dn_nblkptr,
			    sizeof (blkptr_t) *
			    (dn->dn_next_nblkptr[txgoff] - dnp->dn_nblkptr));
#ifdef ZFS_DEBUG
		} else {
			int i;
			ASSERT(dn->dn_next_nblkptr[txgoff] < dnp->dn_nblkptr);
			/* the blkptrs we are losing better be unallocated */
			for (i = 0; i < dnp->dn_nblkptr; i++) {
				if (i >= dn->dn_next_nblkptr[txgoff])
					ASSERT(BP_IS_HOLE(&dnp->dn_blkptr[i]));
			}
#endif
		}
		mutex_enter(&dn->dn_mtx);
		dnp->dn_nblkptr = dn->dn_next_nblkptr[txgoff];
		dn->dn_next_nblkptr[txgoff] = 0;
		mutex_exit(&dn->dn_mtx);
	}

	dbuf_sync_list(list, dn->dn_phys->dn_nlevels - 1, tx);

	if (!DMU_OBJECT_IS_SPECIAL(dn->dn_object)) {
		ASSERT3P(list_head(list), ==, NULL);
		dnode_rele(dn, (void *)(uintptr_t)tx->tx_txg);
	}

	/*
	 * Although we have dropped our reference to the dnode, it
	 * can't be evicted until its written, and we haven't yet
	 * initiated the IO for the dnode's dbuf.  Additionally, the caller
	 * has already added a reference to the dnode because it's on the
	 * os_synced_dnodes list.
	 */
}