aboutsummaryrefslogtreecommitdiffstats
path: root/module/zfs/zfs_log.c
blob: 4d89cb04b592742b1c951bf06d906cd40de260ca (plain)
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
/*
 * 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.
 */


#include <sys/types.h>
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sysmacros.h>
#include <sys/cmn_err.h>
#include <sys/kmem.h>
#include <sys/thread.h>
#include <sys/file.h>
#include <sys/vfs.h>
#include <sys/zfs_znode.h>
#include <sys/zfs_dir.h>
#include <sys/zil.h>
#include <sys/zil_impl.h>
#include <sys/byteorder.h>
#include <sys/policy.h>
#include <sys/stat.h>
#include <sys/mode.h>
#include <sys/acl.h>
#include <sys/dmu.h>
#include <sys/spa.h>
#include <sys/zfs_fuid.h>
#include <sys/ddi.h>
#include <sys/dsl_dataset.h>

/*
 * These zfs_log_* functions must be called within a dmu tx, in one
 * of 2 contexts depending on zilog->z_replay:
 *
 * Non replay mode
 * ---------------
 * We need to record the transaction so that if it is committed to
 * the Intent Log then it can be replayed.  An intent log transaction
 * structure (itx_t) is allocated and all the information necessary to
 * possibly replay the transaction is saved in it. The itx is then assigned
 * a sequence number and inserted in the in-memory list anchored in the zilog.
 *
 * Replay mode
 * -----------
 * We need to mark the intent log record as replayed in the log header.
 * This is done in the same transaction as the replay so that they
 * commit atomically.
 */

int
zfs_log_create_txtype(zil_create_t type, vsecattr_t *vsecp, vattr_t *vap)
{
	int isxvattr = (vap->va_mask & ATTR_XVATTR);
	switch (type) {
	case Z_FILE:
		if (vsecp == NULL && !isxvattr)
			return (TX_CREATE);
		if (vsecp && isxvattr)
			return (TX_CREATE_ACL_ATTR);
		if (vsecp)
			return (TX_CREATE_ACL);
		else
			return (TX_CREATE_ATTR);
		/*NOTREACHED*/
	case Z_DIR:
		if (vsecp == NULL && !isxvattr)
			return (TX_MKDIR);
		if (vsecp && isxvattr)
			return (TX_MKDIR_ACL_ATTR);
		if (vsecp)
			return (TX_MKDIR_ACL);
		else
			return (TX_MKDIR_ATTR);
	case Z_XATTRDIR:
		return (TX_MKXATTR);
	}
	ASSERT(0);
	return (TX_MAX_TYPE);
}

/*
 * build up the log data necessary for logging xvattr_t
 * First lr_attr_t is initialized.  following the lr_attr_t
 * is the mapsize and attribute bitmap copied from the xvattr_t.
 * Following the bitmap and bitmapsize two 64 bit words are reserved
 * for the create time which may be set.  Following the create time
 * records a single 64 bit integer which has the bits to set on
 * replay for the xvattr.
 */
static void
zfs_log_xvattr(lr_attr_t *lrattr, xvattr_t *xvap)
{
	uint32_t	*bitmap;
	uint64_t	*attrs;
	uint64_t	*crtime;
	xoptattr_t	*xoap;
	void		*scanstamp;
	int		i;

	xoap = xva_getxoptattr(xvap);
	ASSERT(xoap);

	lrattr->lr_attr_masksize = xvap->xva_mapsize;
	bitmap = &lrattr->lr_attr_bitmap;
	for (i = 0; i != xvap->xva_mapsize; i++, bitmap++) {
		*bitmap = xvap->xva_reqattrmap[i];
	}

	/* Now pack the attributes up in a single uint64_t */
	attrs = (uint64_t *)bitmap;
	crtime = attrs + 1;
	scanstamp = (caddr_t)(crtime + 2);
	*attrs = 0;
	if (XVA_ISSET_REQ(xvap, XAT_READONLY))
		*attrs |= (xoap->xoa_readonly == 0) ? 0 :
		    XAT0_READONLY;
	if (XVA_ISSET_REQ(xvap, XAT_HIDDEN))
		*attrs |= (xoap->xoa_hidden == 0) ? 0 :
		    XAT0_HIDDEN;
	if (XVA_ISSET_REQ(xvap, XAT_SYSTEM))
		*attrs |= (xoap->xoa_system == 0) ? 0 :
		    XAT0_SYSTEM;
	if (XVA_ISSET_REQ(xvap, XAT_ARCHIVE))
		*attrs |= (xoap->xoa_archive == 0) ? 0 :
		    XAT0_ARCHIVE;
	if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE))
		*attrs |= (xoap->xoa_immutable == 0) ? 0 :
		    XAT0_IMMUTABLE;
	if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK))
		*attrs |= (xoap->xoa_nounlink == 0) ? 0 :
		    XAT0_NOUNLINK;
	if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY))
		*attrs |= (xoap->xoa_appendonly == 0) ? 0 :
		    XAT0_APPENDONLY;
	if (XVA_ISSET_REQ(xvap, XAT_OPAQUE))
		*attrs |= (xoap->xoa_opaque == 0) ? 0 :
		    XAT0_APPENDONLY;
	if (XVA_ISSET_REQ(xvap, XAT_NODUMP))
		*attrs |= (xoap->xoa_nodump == 0) ? 0 :
		    XAT0_NODUMP;
	if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED))
		*attrs |= (xoap->xoa_av_quarantined == 0) ? 0 :
		    XAT0_AV_QUARANTINED;
	if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED))
		*attrs |= (xoap->xoa_av_modified == 0) ? 0 :
		    XAT0_AV_MODIFIED;
	if (XVA_ISSET_REQ(xvap, XAT_CREATETIME))
		ZFS_TIME_ENCODE(&xoap->xoa_createtime, crtime);
	if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP))
		bcopy(xoap->xoa_av_scanstamp, scanstamp, AV_SCANSTAMP_SZ);
	if (XVA_ISSET_REQ(xvap, XAT_REPARSE))
		*attrs |= (xoap->xoa_reparse == 0) ? 0 :
		    XAT0_REPARSE;
	if (XVA_ISSET_REQ(xvap, XAT_OFFLINE))
		*attrs |= (xoap->xoa_offline == 0) ? 0 :
		    XAT0_OFFLINE;
	if (XVA_ISSET_REQ(xvap, XAT_SPARSE))
		*attrs |= (xoap->xoa_sparse == 0) ? 0 :
		    XAT0_SPARSE;
}

static void *
zfs_log_fuid_ids(zfs_fuid_info_t *fuidp, void *start)
{
	zfs_fuid_t *zfuid;
	uint64_t *fuidloc = start;

	/* First copy in the ACE FUIDs */
	for (zfuid = list_head(&fuidp->z_fuids); zfuid;
	    zfuid = list_next(&fuidp->z_fuids, zfuid)) {
		*fuidloc++ = zfuid->z_logfuid;
	}
	return (fuidloc);
}


static void *
zfs_log_fuid_domains(zfs_fuid_info_t *fuidp, void *start)
{
	zfs_fuid_domain_t *zdomain;

	/* now copy in the domain info, if any */
	if (fuidp->z_domain_str_sz != 0) {
		for (zdomain = list_head(&fuidp->z_domains); zdomain;
		    zdomain = list_next(&fuidp->z_domains, zdomain)) {
			bcopy((void *)zdomain->z_domain, start,
			    strlen(zdomain->z_domain) + 1);
			start = (caddr_t)start +
			    strlen(zdomain->z_domain) + 1;
		}
	}
	return (start);
}

/*
 * Handles TX_CREATE, TX_CREATE_ATTR, TX_MKDIR, TX_MKDIR_ATTR and
 * TK_MKXATTR transactions.
 *
 * TX_CREATE and TX_MKDIR are standard creates, but they may have FUID
 * domain information appended prior to the name.  In this case the
 * uid/gid in the log record will be a log centric FUID.
 *
 * TX_CREATE_ACL_ATTR and TX_MKDIR_ACL_ATTR handle special creates that
 * may contain attributes, ACL and optional fuid information.
 *
 * TX_CREATE_ACL and TX_MKDIR_ACL handle special creates that specify
 * and ACL and normal users/groups in the ACEs.
 *
 * There may be an optional xvattr attribute information similar
 * to zfs_log_setattr.
 *
 * Also, after the file name "domain" strings may be appended.
 */
void
zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *dzp, znode_t *zp, char *name, vsecattr_t *vsecp,
    zfs_fuid_info_t *fuidp, vattr_t *vap)
{
	itx_t *itx;
	lr_create_t *lr;
	lr_acl_create_t *lracl;
	size_t aclsize = 0;
	size_t xvatsize = 0;
	size_t txsize;
	xvattr_t *xvap = (xvattr_t *)vap;
	void *end;
	size_t lrsize;
	size_t namesize = strlen(name) + 1;
	size_t fuidsz = 0;

	if (zil_replaying(zilog, tx))
		return;

	/*
	 * If we have FUIDs present then add in space for
	 * domains and ACE fuid's if any.
	 */
	if (fuidp) {
		fuidsz += fuidp->z_domain_str_sz;
		fuidsz += fuidp->z_fuid_cnt * sizeof (uint64_t);
	}

	if (vap->va_mask & ATTR_XVATTR)
		xvatsize = ZIL_XVAT_SIZE(xvap->xva_mapsize);

	if ((int)txtype == TX_CREATE_ATTR || (int)txtype == TX_MKDIR_ATTR ||
	    (int)txtype == TX_CREATE || (int)txtype == TX_MKDIR ||
	    (int)txtype == TX_MKXATTR) {
		txsize = sizeof (*lr) + namesize + fuidsz + xvatsize;
		lrsize = sizeof (*lr);
	} else {
		txsize =
		    sizeof (lr_acl_create_t) + namesize + fuidsz +
		    ZIL_ACE_LENGTH(aclsize) + xvatsize;
		lrsize = sizeof (lr_acl_create_t);
	}

	itx = zil_itx_create(txtype, txsize);

	lr = (lr_create_t *)&itx->itx_lr;
	lr->lr_doid = dzp->z_id;
	lr->lr_foid = zp->z_id;
	/* Store dnode slot count in 8 bits above object id. */
	LR_FOID_SET_SLOTS(lr->lr_foid, zp->z_dnodesize >> DNODE_SHIFT);
	lr->lr_mode = zp->z_mode;
	if (!IS_EPHEMERAL(zp->z_uid)) {
		lr->lr_uid = (uint64_t)zp->z_uid;
	} else {
		lr->lr_uid = fuidp->z_fuid_owner;
	}
	if (!IS_EPHEMERAL(zp->z_gid)) {
		lr->lr_gid = (uint64_t)zp->z_gid;
	} else {
		lr->lr_gid = fuidp->z_fuid_group;
	}
	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &lr->lr_gen,
	    sizeof (uint64_t));
	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(ZTOZSB(zp)),
	    lr->lr_crtime, sizeof (uint64_t) * 2);

	if (sa_lookup(zp->z_sa_hdl, SA_ZPL_RDEV(ZTOZSB(zp)), &lr->lr_rdev,
	    sizeof (lr->lr_rdev)) != 0)
		lr->lr_rdev = 0;

	/*
	 * Fill in xvattr info if any
	 */
	if (vap->va_mask & ATTR_XVATTR) {
		zfs_log_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), xvap);
		end = (caddr_t)lr + lrsize + xvatsize;
	} else {
		end = (caddr_t)lr + lrsize;
	}

	/* Now fill in any ACL info */

	if (vsecp) {
		lracl = (lr_acl_create_t *)&itx->itx_lr;
		lracl->lr_aclcnt = vsecp->vsa_aclcnt;
		lracl->lr_acl_bytes = aclsize;
		lracl->lr_domcnt = fuidp ? fuidp->z_domain_cnt : 0;
		lracl->lr_fuidcnt  = fuidp ? fuidp->z_fuid_cnt : 0;
		if (vsecp->vsa_aclflags & VSA_ACE_ACLFLAGS)
			lracl->lr_acl_flags = (uint64_t)vsecp->vsa_aclflags;
		else
			lracl->lr_acl_flags = 0;

		bcopy(vsecp->vsa_aclentp, end, aclsize);
		end = (caddr_t)end + ZIL_ACE_LENGTH(aclsize);
	}

	/* drop in FUID info */
	if (fuidp) {
		end = zfs_log_fuid_ids(fuidp, end);
		end = zfs_log_fuid_domains(fuidp, end);
	}
	/*
	 * Now place file name in log record
	 */
	bcopy(name, end, namesize);

	zil_itx_assign(zilog, itx, tx);
}

/*
 * Handles both TX_REMOVE and TX_RMDIR transactions.
 */
void
zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
	znode_t *dzp, char *name, uint64_t foid)
{
	itx_t *itx;
	lr_remove_t *lr;
	size_t namesize = strlen(name) + 1;

	if (zil_replaying(zilog, tx))
		return;

	itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
	lr = (lr_remove_t *)&itx->itx_lr;
	lr->lr_doid = dzp->z_id;
	bcopy(name, (char *)(lr + 1), namesize);

	itx->itx_oid = foid;

	zil_itx_assign(zilog, itx, tx);
}

/*
 * Handles TX_LINK transactions.
 */
void
zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
	znode_t *dzp, znode_t *zp, char *name)
{
	itx_t *itx;
	lr_link_t *lr;
	size_t namesize = strlen(name) + 1;

	if (zil_replaying(zilog, tx))
		return;

	itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
	lr = (lr_link_t *)&itx->itx_lr;
	lr->lr_doid = dzp->z_id;
	lr->lr_link_obj = zp->z_id;
	bcopy(name, (char *)(lr + 1), namesize);

	zil_itx_assign(zilog, itx, tx);
}

/*
 * Handles TX_SYMLINK transactions.
 */
void
zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *dzp, znode_t *zp, char *name, char *link)
{
	itx_t *itx;
	lr_create_t *lr;
	size_t namesize = strlen(name) + 1;
	size_t linksize = strlen(link) + 1;

	if (zil_replaying(zilog, tx))
		return;

	itx = zil_itx_create(txtype, sizeof (*lr) + namesize + linksize);
	lr = (lr_create_t *)&itx->itx_lr;
	lr->lr_doid = dzp->z_id;
	lr->lr_foid = zp->z_id;
	lr->lr_uid = zp->z_uid;
	lr->lr_gid = zp->z_gid;
	lr->lr_mode = zp->z_mode;
	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &lr->lr_gen,
	    sizeof (uint64_t));
	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(ZTOZSB(zp)),
	    lr->lr_crtime, sizeof (uint64_t) * 2);
	bcopy(name, (char *)(lr + 1), namesize);
	bcopy(link, (char *)(lr + 1) + namesize, linksize);

	zil_itx_assign(zilog, itx, tx);
}

/*
 * Handles TX_RENAME transactions.
 */
void
zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
	znode_t *sdzp, char *sname, znode_t *tdzp, char *dname, znode_t *szp)
{
	itx_t *itx;
	lr_rename_t *lr;
	size_t snamesize = strlen(sname) + 1;
	size_t dnamesize = strlen(dname) + 1;

	if (zil_replaying(zilog, tx))
		return;

	itx = zil_itx_create(txtype, sizeof (*lr) + snamesize + dnamesize);
	lr = (lr_rename_t *)&itx->itx_lr;
	lr->lr_sdoid = sdzp->z_id;
	lr->lr_tdoid = tdzp->z_id;
	bcopy(sname, (char *)(lr + 1), snamesize);
	bcopy(dname, (char *)(lr + 1) + snamesize, dnamesize);
	itx->itx_oid = szp->z_id;

	zil_itx_assign(zilog, itx, tx);
}

/*
 * zfs_log_write() handles TX_WRITE transactions. The specified callback is
 * called as soon as the write is on stable storage (be it via a DMU sync or a
 * ZIL commit).
 */
long zfs_immediate_write_sz = 32768;

void
zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
	znode_t *zp, offset_t off, ssize_t resid, int ioflag,
	zil_callback_t callback, void *callback_data)
{
	itx_wr_state_t write_state;
	boolean_t slogging;
	uintptr_t fsync_cnt;
	ssize_t immediate_write_sz;

	if (zil_replaying(zilog, tx) || zp->z_unlinked) {
		if (callback != NULL)
			callback(callback_data);
		return;
	}

	immediate_write_sz = (zilog->zl_logbias == ZFS_LOGBIAS_THROUGHPUT)
	    ? 0 : (ssize_t)zfs_immediate_write_sz;

	slogging = spa_has_slogs(zilog->zl_spa) &&
	    (zilog->zl_logbias == ZFS_LOGBIAS_LATENCY);
	if (resid > immediate_write_sz && !slogging && resid <= zp->z_blksz)
		write_state = WR_INDIRECT;
	else if (ioflag & (FSYNC | FDSYNC))
		write_state = WR_COPIED;
	else
		write_state = WR_NEED_COPY;

	if ((fsync_cnt = (uintptr_t)tsd_get(zfs_fsyncer_key)) != 0) {
		(void) tsd_set(zfs_fsyncer_key, (void *)(fsync_cnt - 1));
	}

	while (resid) {
		itx_t *itx;
		lr_write_t *lr;
		ssize_t len;

		/*
		 * If the write would overflow the largest block then split it.
		 */
		if (write_state != WR_INDIRECT && resid > ZIL_MAX_LOG_DATA)
			len = SPA_OLD_MAXBLOCKSIZE >> 1;
		else
			len = resid;

		itx = zil_itx_create(txtype, sizeof (*lr) +
		    (write_state == WR_COPIED ? len : 0));
		lr = (lr_write_t *)&itx->itx_lr;
		if (write_state == WR_COPIED && dmu_read(ZTOZSB(zp)->z_os,
		    zp->z_id, off, len, lr + 1, DMU_READ_NO_PREFETCH) != 0) {
			zil_itx_destroy(itx);
			itx = zil_itx_create(txtype, sizeof (*lr));
			lr = (lr_write_t *)&itx->itx_lr;
			write_state = WR_NEED_COPY;
		}

		itx->itx_wr_state = write_state;
		if (write_state == WR_NEED_COPY)
			itx->itx_sod += len;
		lr->lr_foid = zp->z_id;
		lr->lr_offset = off;
		lr->lr_length = len;
		lr->lr_blkoff = 0;
		BP_ZERO(&lr->lr_blkptr);

		itx->itx_private = ZTOZSB(zp);

		if (!(ioflag & (FSYNC | FDSYNC)) && (zp->z_sync_cnt == 0) &&
		    (fsync_cnt == 0))
			itx->itx_sync = B_FALSE;

		itx->itx_callback = callback;
		itx->itx_callback_data = callback_data;
		zil_itx_assign(zilog, itx, tx);

		off += len;
		resid -= len;
	}
}

/*
 * Handles TX_TRUNCATE transactions.
 */
void
zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
	znode_t *zp, uint64_t off, uint64_t len)
{
	itx_t *itx;
	lr_truncate_t *lr;

	if (zil_replaying(zilog, tx) || zp->z_unlinked)
		return;

	itx = zil_itx_create(txtype, sizeof (*lr));
	lr = (lr_truncate_t *)&itx->itx_lr;
	lr->lr_foid = zp->z_id;
	lr->lr_offset = off;
	lr->lr_length = len;

	itx->itx_sync = (zp->z_sync_cnt != 0);
	zil_itx_assign(zilog, itx, tx);
}

/*
 * Handles TX_SETATTR transactions.
 */
void
zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype,
    znode_t *zp, vattr_t *vap, uint_t mask_applied, zfs_fuid_info_t *fuidp)
{
	itx_t		*itx;
	lr_setattr_t	*lr;
	xvattr_t	*xvap = (xvattr_t *)vap;
	size_t		recsize = sizeof (lr_setattr_t);
	void		*start;

	if (zil_replaying(zilog, tx) || zp->z_unlinked)
		return;

	/*
	 * If XVATTR set, then log record size needs to allow
	 * for lr_attr_t + xvattr mask, mapsize and create time
	 * plus actual attribute values
	 */
	if (vap->va_mask & ATTR_XVATTR)
		recsize = sizeof (*lr) + ZIL_XVAT_SIZE(xvap->xva_mapsize);

	if (fuidp)
		recsize += fuidp->z_domain_str_sz;

	itx = zil_itx_create(txtype, recsize);
	lr = (lr_setattr_t *)&itx->itx_lr;
	lr->lr_foid = zp->z_id;
	lr->lr_mask = (uint64_t)mask_applied;
	lr->lr_mode = (uint64_t)vap->va_mode;
	if ((mask_applied & ATTR_UID) && IS_EPHEMERAL(vap->va_uid))
		lr->lr_uid = fuidp->z_fuid_owner;
	else
		lr->lr_uid = (uint64_t)vap->va_uid;

	if ((mask_applied & ATTR_GID) && IS_EPHEMERAL(vap->va_gid))
		lr->lr_gid = fuidp->z_fuid_group;
	else
		lr->lr_gid = (uint64_t)vap->va_gid;

	lr->lr_size = (uint64_t)vap->va_size;
	ZFS_TIME_ENCODE(&vap->va_atime, lr->lr_atime);
	ZFS_TIME_ENCODE(&vap->va_mtime, lr->lr_mtime);
	start = (lr_setattr_t *)(lr + 1);
	if (vap->va_mask & ATTR_XVATTR) {
		zfs_log_xvattr((lr_attr_t *)start, xvap);
		start = (caddr_t)start + ZIL_XVAT_SIZE(xvap->xva_mapsize);
	}

	/*
	 * Now stick on domain information if any on end
	 */

	if (fuidp)
		(void) zfs_log_fuid_domains(fuidp, start);

	itx->itx_sync = (zp->z_sync_cnt != 0);
	zil_itx_assign(zilog, itx, tx);
}

/*
 * Handles TX_ACL transactions.
 */
void
zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
    vsecattr_t *vsecp, zfs_fuid_info_t *fuidp)
{
	itx_t *itx;
	lr_acl_v0_t *lrv0;
	lr_acl_t *lr;
	int txtype;
	int lrsize;
	size_t txsize;
	size_t aclbytes = vsecp->vsa_aclentsz;

	if (zil_replaying(zilog, tx) || zp->z_unlinked)
		return;

	txtype = (ZTOZSB(zp)->z_version < ZPL_VERSION_FUID) ?
	    TX_ACL_V0 : TX_ACL;

	if (txtype == TX_ACL)
		lrsize = sizeof (*lr);
	else
		lrsize = sizeof (*lrv0);

	txsize = lrsize +
	    ((txtype == TX_ACL) ? ZIL_ACE_LENGTH(aclbytes) : aclbytes) +
	    (fuidp ? fuidp->z_domain_str_sz : 0) +
	    sizeof (uint64_t) * (fuidp ? fuidp->z_fuid_cnt : 0);

	itx = zil_itx_create(txtype, txsize);

	lr = (lr_acl_t *)&itx->itx_lr;
	lr->lr_foid = zp->z_id;
	if (txtype == TX_ACL) {
		lr->lr_acl_bytes = aclbytes;
		lr->lr_domcnt = fuidp ? fuidp->z_domain_cnt : 0;
		lr->lr_fuidcnt = fuidp ? fuidp->z_fuid_cnt : 0;
		if (vsecp->vsa_mask & VSA_ACE_ACLFLAGS)
			lr->lr_acl_flags = (uint64_t)vsecp->vsa_aclflags;
		else
			lr->lr_acl_flags = 0;
	}
	lr->lr_aclcnt = (uint64_t)vsecp->vsa_aclcnt;

	if (txtype == TX_ACL_V0) {
		lrv0 = (lr_acl_v0_t *)lr;
		bcopy(vsecp->vsa_aclentp, (ace_t *)(lrv0 + 1), aclbytes);
	} else {
		void *start = (ace_t *)(lr + 1);

		bcopy(vsecp->vsa_aclentp, start, aclbytes);

		start = (caddr_t)start + ZIL_ACE_LENGTH(aclbytes);

		if (fuidp) {
			start = zfs_log_fuid_ids(fuidp, start);
			(void) zfs_log_fuid_domains(fuidp, start);
		}
	}

	itx->itx_sync = (zp->z_sync_cnt != 0);
	zil_itx_assign(zilog, itx, tx);
}

#if defined(_KERNEL) && defined(HAVE_SPL)
module_param(zfs_immediate_write_sz, long, 0644);
MODULE_PARM_DESC(zfs_immediate_write_sz, "Largest data block to write to zil");
#endif