-
Notifications
You must be signed in to change notification settings - Fork 1.8k
/
Copy pathkernel.c
1484 lines (1256 loc) · 29.3 KB
/
kernel.c
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
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: CDDL-1.0
/*
* 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 https://opensource.org/licenses/CDDL-1.0.
* 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, 2018 by Delphix. All rights reserved.
* Copyright (c) 2016 Actifio, Inc. All rights reserved.
*/
#include <assert.h>
#include <fcntl.h>
#include <libgen.h>
#include <poll.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <limits.h>
#include <libzutil.h>
#include <sys/crypto/icp.h>
#include <sys/processor.h>
#include <sys/rrwlock.h>
#include <sys/spa.h>
#include <sys/stat.h>
#include <sys/systeminfo.h>
#include <sys/time.h>
#include <sys/utsname.h>
#include <sys/zfs_context.h>
#include <sys/zfs_onexit.h>
#include <sys/zfs_vfsops.h>
#include <sys/zstd/zstd.h>
#include <sys/zvol.h>
#include <zfs_fletcher.h>
#include <zlib.h>
/*
* Emulation of kernel services in userland.
*/
uint64_t physmem;
uint32_t hostid;
struct utsname hw_utsname;
/* If set, all blocks read will be copied to the specified directory. */
char *vn_dumpdir = NULL;
/* this only exists to have its address taken */
struct proc p0;
/*
* =========================================================================
* threads
* =========================================================================
*
* TS_STACK_MIN is dictated by the minimum allowed pthread stack size. While
* TS_STACK_MAX is somewhat arbitrary, it was selected to be large enough for
* the expected stack depth while small enough to avoid exhausting address
* space with high thread counts.
*/
#define TS_STACK_MIN MAX(PTHREAD_STACK_MIN, 32768)
#define TS_STACK_MAX (256 * 1024)
struct zk_thread_wrapper {
void (*func)(void *);
void *arg;
};
static void *
zk_thread_wrapper(void *arg)
{
struct zk_thread_wrapper ztw;
memcpy(&ztw, arg, sizeof (ztw));
free(arg);
ztw.func(ztw.arg);
return (NULL);
}
kthread_t *
zk_thread_create(const char *name, void (*func)(void *), void *arg,
size_t stksize, int state)
{
pthread_attr_t attr;
pthread_t tid;
char *stkstr;
struct zk_thread_wrapper *ztw;
int detachstate = PTHREAD_CREATE_DETACHED;
VERIFY0(pthread_attr_init(&attr));
if (state & TS_JOINABLE)
detachstate = PTHREAD_CREATE_JOINABLE;
VERIFY0(pthread_attr_setdetachstate(&attr, detachstate));
/*
* We allow the default stack size in user space to be specified by
* setting the ZFS_STACK_SIZE environment variable. This allows us
* the convenience of observing and debugging stack overruns in
* user space. Explicitly specified stack sizes will be honored.
* The usage of ZFS_STACK_SIZE is discussed further in the
* ENVIRONMENT VARIABLES sections of the ztest(1) man page.
*/
if (stksize == 0) {
stkstr = getenv("ZFS_STACK_SIZE");
if (stkstr == NULL)
stksize = TS_STACK_MAX;
else
stksize = MAX(atoi(stkstr), TS_STACK_MIN);
}
VERIFY3S(stksize, >, 0);
stksize = P2ROUNDUP(MAX(stksize, TS_STACK_MIN), PAGESIZE);
/*
* If this ever fails, it may be because the stack size is not a
* multiple of system page size.
*/
VERIFY0(pthread_attr_setstacksize(&attr, stksize));
VERIFY0(pthread_attr_setguardsize(&attr, PAGESIZE));
VERIFY(ztw = malloc(sizeof (*ztw)));
ztw->func = func;
ztw->arg = arg;
VERIFY0(pthread_create(&tid, &attr, zk_thread_wrapper, ztw));
VERIFY0(pthread_attr_destroy(&attr));
pthread_setname_np(tid, name);
return ((void *)(uintptr_t)tid);
}
/*
* =========================================================================
* kstats
* =========================================================================
*/
kstat_t *
kstat_create(const char *module, int instance, const char *name,
const char *class, uchar_t type, ulong_t ndata, uchar_t ks_flag)
{
(void) module, (void) instance, (void) name, (void) class, (void) type,
(void) ndata, (void) ks_flag;
return (NULL);
}
void
kstat_install(kstat_t *ksp)
{
(void) ksp;
}
void
kstat_delete(kstat_t *ksp)
{
(void) ksp;
}
void
kstat_set_raw_ops(kstat_t *ksp,
int (*headers)(char *buf, size_t size),
int (*data)(char *buf, size_t size, void *data),
void *(*addr)(kstat_t *ksp, loff_t index))
{
(void) ksp, (void) headers, (void) data, (void) addr;
}
/*
* =========================================================================
* mutexes
* =========================================================================
*/
void
mutex_init(kmutex_t *mp, char *name, int type, void *cookie)
{
(void) name, (void) type, (void) cookie;
VERIFY0(pthread_mutex_init(&mp->m_lock, NULL));
memset(&mp->m_owner, 0, sizeof (pthread_t));
}
void
mutex_destroy(kmutex_t *mp)
{
VERIFY0(pthread_mutex_destroy(&mp->m_lock));
}
void
mutex_enter(kmutex_t *mp)
{
VERIFY0(pthread_mutex_lock(&mp->m_lock));
mp->m_owner = pthread_self();
}
int
mutex_enter_check_return(kmutex_t *mp)
{
int error = pthread_mutex_lock(&mp->m_lock);
if (error == 0)
mp->m_owner = pthread_self();
return (error);
}
int
mutex_tryenter(kmutex_t *mp)
{
int error = pthread_mutex_trylock(&mp->m_lock);
if (error == 0) {
mp->m_owner = pthread_self();
return (1);
} else {
VERIFY3S(error, ==, EBUSY);
return (0);
}
}
void
mutex_exit(kmutex_t *mp)
{
memset(&mp->m_owner, 0, sizeof (pthread_t));
VERIFY0(pthread_mutex_unlock(&mp->m_lock));
}
/*
* =========================================================================
* rwlocks
* =========================================================================
*/
void
rw_init(krwlock_t *rwlp, char *name, int type, void *arg)
{
(void) name, (void) type, (void) arg;
VERIFY0(pthread_rwlock_init(&rwlp->rw_lock, NULL));
rwlp->rw_readers = 0;
rwlp->rw_owner = 0;
}
void
rw_destroy(krwlock_t *rwlp)
{
VERIFY0(pthread_rwlock_destroy(&rwlp->rw_lock));
}
void
rw_enter(krwlock_t *rwlp, krw_t rw)
{
if (rw == RW_READER) {
VERIFY0(pthread_rwlock_rdlock(&rwlp->rw_lock));
atomic_inc_uint(&rwlp->rw_readers);
} else {
VERIFY0(pthread_rwlock_wrlock(&rwlp->rw_lock));
rwlp->rw_owner = pthread_self();
}
}
void
rw_exit(krwlock_t *rwlp)
{
if (RW_READ_HELD(rwlp))
atomic_dec_uint(&rwlp->rw_readers);
else
rwlp->rw_owner = 0;
VERIFY0(pthread_rwlock_unlock(&rwlp->rw_lock));
}
int
rw_tryenter(krwlock_t *rwlp, krw_t rw)
{
int error;
if (rw == RW_READER)
error = pthread_rwlock_tryrdlock(&rwlp->rw_lock);
else
error = pthread_rwlock_trywrlock(&rwlp->rw_lock);
if (error == 0) {
if (rw == RW_READER)
atomic_inc_uint(&rwlp->rw_readers);
else
rwlp->rw_owner = pthread_self();
return (1);
}
VERIFY3S(error, ==, EBUSY);
return (0);
}
uint32_t
zone_get_hostid(void *zonep)
{
/*
* We're emulating the system's hostid in userland.
*/
(void) zonep;
return (hostid);
}
int
rw_tryupgrade(krwlock_t *rwlp)
{
(void) rwlp;
return (0);
}
/*
* =========================================================================
* condition variables
* =========================================================================
*/
void
cv_init(kcondvar_t *cv, char *name, int type, void *arg)
{
(void) name, (void) type, (void) arg;
VERIFY0(pthread_cond_init(cv, NULL));
}
void
cv_destroy(kcondvar_t *cv)
{
VERIFY0(pthread_cond_destroy(cv));
}
void
cv_wait(kcondvar_t *cv, kmutex_t *mp)
{
memset(&mp->m_owner, 0, sizeof (pthread_t));
VERIFY0(pthread_cond_wait(cv, &mp->m_lock));
mp->m_owner = pthread_self();
}
int
cv_wait_sig(kcondvar_t *cv, kmutex_t *mp)
{
cv_wait(cv, mp);
return (1);
}
int
cv_timedwait(kcondvar_t *cv, kmutex_t *mp, clock_t abstime)
{
int error;
struct timeval tv;
struct timespec ts;
clock_t delta;
delta = abstime - ddi_get_lbolt();
if (delta <= 0)
return (-1);
VERIFY(gettimeofday(&tv, NULL) == 0);
ts.tv_sec = tv.tv_sec + delta / hz;
ts.tv_nsec = tv.tv_usec * NSEC_PER_USEC + (delta % hz) * (NANOSEC / hz);
if (ts.tv_nsec >= NANOSEC) {
ts.tv_sec++;
ts.tv_nsec -= NANOSEC;
}
memset(&mp->m_owner, 0, sizeof (pthread_t));
error = pthread_cond_timedwait(cv, &mp->m_lock, &ts);
mp->m_owner = pthread_self();
if (error == ETIMEDOUT)
return (-1);
VERIFY0(error);
return (1);
}
int
cv_timedwait_hires(kcondvar_t *cv, kmutex_t *mp, hrtime_t tim, hrtime_t res,
int flag)
{
(void) res;
int error;
struct timeval tv;
struct timespec ts;
hrtime_t delta;
ASSERT(flag == 0 || flag == CALLOUT_FLAG_ABSOLUTE);
delta = tim;
if (flag & CALLOUT_FLAG_ABSOLUTE)
delta -= gethrtime();
if (delta <= 0)
return (-1);
VERIFY0(gettimeofday(&tv, NULL));
ts.tv_sec = tv.tv_sec + delta / NANOSEC;
ts.tv_nsec = tv.tv_usec * NSEC_PER_USEC + (delta % NANOSEC);
if (ts.tv_nsec >= NANOSEC) {
ts.tv_sec++;
ts.tv_nsec -= NANOSEC;
}
memset(&mp->m_owner, 0, sizeof (pthread_t));
error = pthread_cond_timedwait(cv, &mp->m_lock, &ts);
mp->m_owner = pthread_self();
if (error == ETIMEDOUT)
return (-1);
VERIFY0(error);
return (1);
}
void
cv_signal(kcondvar_t *cv)
{
VERIFY0(pthread_cond_signal(cv));
}
void
cv_broadcast(kcondvar_t *cv)
{
VERIFY0(pthread_cond_broadcast(cv));
}
/*
* =========================================================================
* procfs list
* =========================================================================
*/
void
seq_printf(struct seq_file *m, const char *fmt, ...)
{
(void) m, (void) fmt;
}
void
procfs_list_install(const char *module,
const char *submodule,
const char *name,
mode_t mode,
procfs_list_t *procfs_list,
int (*show)(struct seq_file *f, void *p),
int (*show_header)(struct seq_file *f),
int (*clear)(procfs_list_t *procfs_list),
size_t procfs_list_node_off)
{
(void) module, (void) submodule, (void) name, (void) mode, (void) show,
(void) show_header, (void) clear;
mutex_init(&procfs_list->pl_lock, NULL, MUTEX_DEFAULT, NULL);
list_create(&procfs_list->pl_list,
procfs_list_node_off + sizeof (procfs_list_node_t),
procfs_list_node_off + offsetof(procfs_list_node_t, pln_link));
procfs_list->pl_next_id = 1;
procfs_list->pl_node_offset = procfs_list_node_off;
}
void
procfs_list_uninstall(procfs_list_t *procfs_list)
{
(void) procfs_list;
}
void
procfs_list_destroy(procfs_list_t *procfs_list)
{
ASSERT(list_is_empty(&procfs_list->pl_list));
list_destroy(&procfs_list->pl_list);
mutex_destroy(&procfs_list->pl_lock);
}
#define NODE_ID(procfs_list, obj) \
(((procfs_list_node_t *)(((char *)obj) + \
(procfs_list)->pl_node_offset))->pln_id)
void
procfs_list_add(procfs_list_t *procfs_list, void *p)
{
ASSERT(MUTEX_HELD(&procfs_list->pl_lock));
NODE_ID(procfs_list, p) = procfs_list->pl_next_id++;
list_insert_tail(&procfs_list->pl_list, p);
}
/*
* =========================================================================
* vnode operations
* =========================================================================
*/
/*
* =========================================================================
* Figure out which debugging statements to print
* =========================================================================
*/
static char *dprintf_string;
static int dprintf_print_all;
int
dprintf_find_string(const char *string)
{
char *tmp_str = dprintf_string;
int len = strlen(string);
/*
* Find out if this is a string we want to print.
* String format: file1.c,function_name1,file2.c,file3.c
*/
while (tmp_str != NULL) {
if (strncmp(tmp_str, string, len) == 0 &&
(tmp_str[len] == ',' || tmp_str[len] == '\0'))
return (1);
tmp_str = strchr(tmp_str, ',');
if (tmp_str != NULL)
tmp_str++; /* Get rid of , */
}
return (0);
}
void
dprintf_setup(int *argc, char **argv)
{
int i, j;
/*
* Debugging can be specified two ways: by setting the
* environment variable ZFS_DEBUG, or by including a
* "debug=..." argument on the command line. The command
* line setting overrides the environment variable.
*/
for (i = 1; i < *argc; i++) {
int len = strlen("debug=");
/* First look for a command line argument */
if (strncmp("debug=", argv[i], len) == 0) {
dprintf_string = argv[i] + len;
/* Remove from args */
for (j = i; j < *argc; j++)
argv[j] = argv[j+1];
argv[j] = NULL;
(*argc)--;
}
}
if (dprintf_string == NULL) {
/* Look for ZFS_DEBUG environment variable */
dprintf_string = getenv("ZFS_DEBUG");
}
/*
* Are we just turning on all debugging?
*/
if (dprintf_find_string("on"))
dprintf_print_all = 1;
if (dprintf_string != NULL)
zfs_flags |= ZFS_DEBUG_DPRINTF;
}
/*
* =========================================================================
* debug printfs
* =========================================================================
*/
void
__dprintf(boolean_t dprint, const char *file, const char *func,
int line, const char *fmt, ...)
{
/* Get rid of annoying "../common/" prefix to filename. */
const char *newfile = zfs_basename(file);
va_list adx;
if (dprint) {
/* dprintf messages are printed immediately */
if (!dprintf_print_all &&
!dprintf_find_string(newfile) &&
!dprintf_find_string(func))
return;
/* Print out just the function name if requested */
flockfile(stdout);
if (dprintf_find_string("pid"))
(void) printf("%d ", getpid());
if (dprintf_find_string("tid"))
(void) printf("%ju ",
(uintmax_t)(uintptr_t)pthread_self());
if (dprintf_find_string("cpu"))
(void) printf("%u ", getcpuid());
if (dprintf_find_string("time"))
(void) printf("%llu ", gethrtime());
if (dprintf_find_string("long"))
(void) printf("%s, line %d: ", newfile, line);
(void) printf("dprintf: %s: ", func);
va_start(adx, fmt);
(void) vprintf(fmt, adx);
va_end(adx);
funlockfile(stdout);
} else {
/* zfs_dbgmsg is logged for dumping later */
size_t size;
char *buf;
int i;
size = 1024;
buf = umem_alloc(size, UMEM_NOFAIL);
i = snprintf(buf, size, "%s:%d:%s(): ", newfile, line, func);
if (i < size) {
va_start(adx, fmt);
(void) vsnprintf(buf + i, size - i, fmt, adx);
va_end(adx);
}
__zfs_dbgmsg(buf);
umem_free(buf, size);
}
}
/*
* =========================================================================
* cmn_err() and panic()
* =========================================================================
*/
static char ce_prefix[CE_IGNORE][10] = { "", "NOTICE: ", "WARNING: ", "" };
static char ce_suffix[CE_IGNORE][2] = { "", "\n", "\n", "" };
__attribute__((noreturn)) void
vpanic(const char *fmt, va_list adx)
{
(void) fprintf(stderr, "error: ");
(void) vfprintf(stderr, fmt, adx);
(void) fprintf(stderr, "\n");
abort(); /* think of it as a "user-level crash dump" */
}
__attribute__((noreturn)) void
panic(const char *fmt, ...)
{
va_list adx;
va_start(adx, fmt);
vpanic(fmt, adx);
va_end(adx);
}
void
vcmn_err(int ce, const char *fmt, va_list adx)
{
if (ce == CE_PANIC)
vpanic(fmt, adx);
if (ce != CE_NOTE) { /* suppress noise in userland stress testing */
(void) fprintf(stderr, "%s", ce_prefix[ce]);
(void) vfprintf(stderr, fmt, adx);
(void) fprintf(stderr, "%s", ce_suffix[ce]);
}
}
void
cmn_err(int ce, const char *fmt, ...)
{
va_list adx;
va_start(adx, fmt);
vcmn_err(ce, fmt, adx);
va_end(adx);
}
/*
* =========================================================================
* misc routines
* =========================================================================
*/
void
delay(clock_t ticks)
{
(void) poll(0, 0, ticks * (1000 / hz));
}
/*
* Find highest one bit set.
* Returns bit number + 1 of highest bit that is set, otherwise returns 0.
* The __builtin_clzll() function is supported by both GCC and Clang.
*/
int
highbit64(uint64_t i)
{
if (i == 0)
return (0);
return (NBBY * sizeof (uint64_t) - __builtin_clzll(i));
}
/*
* Find lowest one bit set.
* Returns bit number + 1 of lowest bit that is set, otherwise returns 0.
* The __builtin_ffsll() function is supported by both GCC and Clang.
*/
int
lowbit64(uint64_t i)
{
if (i == 0)
return (0);
return (__builtin_ffsll(i));
}
const char *random_path = "/dev/random";
const char *urandom_path = "/dev/urandom";
static int random_fd = -1, urandom_fd = -1;
void
random_init(void)
{
VERIFY((random_fd = open(random_path, O_RDONLY | O_CLOEXEC)) != -1);
VERIFY((urandom_fd = open(urandom_path, O_RDONLY | O_CLOEXEC)) != -1);
}
void
random_fini(void)
{
close(random_fd);
close(urandom_fd);
random_fd = -1;
urandom_fd = -1;
}
static int
random_get_bytes_common(uint8_t *ptr, size_t len, int fd)
{
size_t resid = len;
ssize_t bytes;
ASSERT(fd != -1);
while (resid != 0) {
bytes = read(fd, ptr, resid);
ASSERT3S(bytes, >=, 0);
ptr += bytes;
resid -= bytes;
}
return (0);
}
int
random_get_bytes(uint8_t *ptr, size_t len)
{
return (random_get_bytes_common(ptr, len, random_fd));
}
int
random_get_pseudo_bytes(uint8_t *ptr, size_t len)
{
return (random_get_bytes_common(ptr, len, urandom_fd));
}
int
ddi_strtoull(const char *str, char **nptr, int base, u_longlong_t *result)
{
errno = 0;
*result = strtoull(str, nptr, base);
if (*result == 0)
return (errno);
return (0);
}
utsname_t *
utsname(void)
{
return (&hw_utsname);
}
/*
* =========================================================================
* kernel emulation setup & teardown
* =========================================================================
*/
static int
umem_out_of_memory(void)
{
char errmsg[] = "out of memory -- generating core dump\n";
(void) fprintf(stderr, "%s", errmsg);
abort();
return (0);
}
void
kernel_init(int mode)
{
extern uint_t rrw_tsd_key;
umem_nofail_callback(umem_out_of_memory);
physmem = sysconf(_SC_PHYS_PAGES);
dprintf("physmem = %llu pages (%.2f GB)\n", (u_longlong_t)physmem,
(double)physmem * sysconf(_SC_PAGE_SIZE) / (1ULL << 30));
hostid = (mode & SPA_MODE_WRITE) ? get_system_hostid() : 0;
random_init();
VERIFY0(uname(&hw_utsname));
system_taskq_init();
icp_init();
zstd_init();
spa_init((spa_mode_t)mode);
fletcher_4_init();
tsd_create(&rrw_tsd_key, rrw_tsd_destroy);
}
void
kernel_fini(void)
{
fletcher_4_fini();
spa_fini();
zstd_fini();
icp_fini();
system_taskq_fini();
random_fini();
}
uid_t
crgetuid(cred_t *cr)
{
(void) cr;
return (0);
}
uid_t
crgetruid(cred_t *cr)
{
(void) cr;
return (0);
}
gid_t
crgetgid(cred_t *cr)
{
(void) cr;
return (0);
}
int
crgetngroups(cred_t *cr)
{
(void) cr;
return (0);
}
gid_t *
crgetgroups(cred_t *cr)
{
(void) cr;
return (NULL);
}
int
zfs_secpolicy_snapshot_perms(const char *name, cred_t *cr)
{
(void) name, (void) cr;
return (0);
}
int
zfs_secpolicy_rename_perms(const char *from, const char *to, cred_t *cr)
{
(void) from, (void) to, (void) cr;
return (0);
}
int
zfs_secpolicy_destroy_perms(const char *name, cred_t *cr)
{
(void) name, (void) cr;
return (0);
}
int
secpolicy_zfs(const cred_t *cr)
{
(void) cr;
return (0);
}
int
secpolicy_zfs_proc(const cred_t *cr, proc_t *proc)
{
(void) cr, (void) proc;
return (0);
}
ksiddomain_t *
ksid_lookupdomain(const char *dom)
{
ksiddomain_t *kd;
kd = umem_zalloc(sizeof (ksiddomain_t), UMEM_NOFAIL);
kd->kd_name = spa_strdup(dom);
return (kd);
}
void
ksiddomain_rele(ksiddomain_t *ksid)
{
spa_strfree(ksid->kd_name);
umem_free(ksid, sizeof (ksiddomain_t));
}
char *
kmem_vasprintf(const char *fmt, va_list adx)
{
char *buf = NULL;
va_list adx_copy;
va_copy(adx_copy, adx);
VERIFY(vasprintf(&buf, fmt, adx_copy) != -1);
va_end(adx_copy);
return (buf);
}
char *
kmem_asprintf(const char *fmt, ...)
{
char *buf = NULL;
va_list adx;
va_start(adx, fmt);
VERIFY(vasprintf(&buf, fmt, adx) != -1);
va_end(adx);
return (buf);
}
/*
* kmem_scnprintf() will return the number of characters that it would have
* printed whenever it is limited by value of the size variable, rather than
* the number of characters that it did print. This can cause misbehavior on
* subsequent uses of the return value, so we define a safe version that will
* return the number of characters actually printed, minus the NULL format
* character. Subsequent use of this by the safe string functions is safe
* whether it is snprintf(), strlcat() or strlcpy().
*/
int
kmem_scnprintf(char *restrict str, size_t size, const char *restrict fmt, ...)
{
int n;
va_list ap;
/* Make the 0 case a no-op so that we do not return -1 */
if (size == 0)
return (0);
va_start(ap, fmt);
n = vsnprintf(str, size, fmt, ap);
va_end(ap);
if (n >= size)
n = size - 1;
return (n);
}
zfs_file_t *