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
|
/*
* 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 2007 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#pragma ident "%Z%%M% %I% %E% SMI"
#include <assert.h>
#include <fcntl.h>
#include <poll.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <zlib.h>
#include <sys/spa.h>
#include <sys/stat.h>
#include <sys/processor.h>
#include <sys/zfs_context.h>
#include <sys/zmod.h>
#include <sys/utsname.h>
/*
* Emulation of kernel services in userland.
*/
int hz = 119; /* frequency when using gethrtime() >> 23 for lbolt */
uint64_t physmem;
vnode_t *rootdir = (vnode_t *)0xabcd1234;
char hw_serial[11];
struct utsname utsname = {
"userland", "libzpool", "1", "1", "na"
};
/*
* =========================================================================
* threads
* =========================================================================
*/
/*ARGSUSED*/
kthread_t *
zk_thread_create(void (*func)(), void *arg)
{
thread_t tid;
VERIFY(thr_create(0, 0, (void *(*)(void *))func, arg, THR_DETACHED,
&tid) == 0);
return ((void *)(uintptr_t)tid);
}
/*
* =========================================================================
* kstats
* =========================================================================
*/
/*ARGSUSED*/
kstat_t *
kstat_create(char *module, int instance, char *name, char *class,
uchar_t type, ulong_t ndata, uchar_t ks_flag)
{
return (NULL);
}
/*ARGSUSED*/
void
kstat_install(kstat_t *ksp)
{}
/*ARGSUSED*/
void
kstat_delete(kstat_t *ksp)
{}
/*
* =========================================================================
* mutexes
* =========================================================================
*/
void
zmutex_init(kmutex_t *mp)
{
mp->m_owner = NULL;
(void) _mutex_init(&mp->m_lock, USYNC_THREAD, NULL);
}
void
zmutex_destroy(kmutex_t *mp)
{
ASSERT(mp->m_owner == NULL);
(void) _mutex_destroy(&(mp)->m_lock);
mp->m_owner = (void *)-1UL;
}
void
mutex_enter(kmutex_t *mp)
{
ASSERT(mp->m_owner != (void *)-1UL);
ASSERT(mp->m_owner != curthread);
VERIFY(mutex_lock(&mp->m_lock) == 0);
ASSERT(mp->m_owner == NULL);
mp->m_owner = curthread;
}
int
mutex_tryenter(kmutex_t *mp)
{
ASSERT(mp->m_owner != (void *)-1UL);
if (mutex_trylock(&mp->m_lock) == 0) {
ASSERT(mp->m_owner == NULL);
mp->m_owner = curthread;
return (1);
} else {
return (0);
}
}
void
mutex_exit(kmutex_t *mp)
{
ASSERT(mp->m_owner == curthread);
mp->m_owner = NULL;
VERIFY(mutex_unlock(&mp->m_lock) == 0);
}
void *
mutex_owner(kmutex_t *mp)
{
return (mp->m_owner);
}
/*
* =========================================================================
* rwlocks
* =========================================================================
*/
/*ARGSUSED*/
void
rw_init(krwlock_t *rwlp, char *name, int type, void *arg)
{
rwlock_init(&rwlp->rw_lock, USYNC_THREAD, NULL);
rwlp->rw_owner = NULL;
rwlp->rw_count = 0;
}
void
rw_destroy(krwlock_t *rwlp)
{
rwlock_destroy(&rwlp->rw_lock);
rwlp->rw_owner = (void *)-1UL;
rwlp->rw_count = -2;
}
void
rw_enter(krwlock_t *rwlp, krw_t rw)
{
//ASSERT(!RW_LOCK_HELD(rwlp));
ASSERT(rwlp->rw_owner != (void *)-1UL);
ASSERT(rwlp->rw_owner != curthread);
if (rw == RW_READER) {
(void) rw_rdlock(&rwlp->rw_lock);
ASSERT(rwlp->rw_count >= 0);
atomic_add_int(&rwlp->rw_count, 1);
} else {
(void) rw_wrlock(&rwlp->rw_lock);
ASSERT(rwlp->rw_count == 0);
rwlp->rw_count = -1;
rwlp->rw_owner = curthread;
}
}
void
rw_exit(krwlock_t *rwlp)
{
ASSERT(rwlp->rw_owner != (void *)-1UL);
if (rwlp->rw_owner == curthread) {
/* Write locked. */
ASSERT(rwlp->rw_count == -1);
rwlp->rw_count = 0;
rwlp->rw_owner = NULL;
} else {
/* Read locked. */
ASSERT(rwlp->rw_count > 0);
atomic_add_int(&rwlp->rw_count, -1);
}
(void) rw_unlock(&rwlp->rw_lock);
}
int
rw_tryenter(krwlock_t *rwlp, krw_t rw)
{
int rv;
ASSERT(rwlp->rw_owner != (void *)-1UL);
ASSERT(rwlp->rw_owner != curthread);
if (rw == RW_READER)
rv = rw_tryrdlock(&rwlp->rw_lock);
else
rv = rw_trywrlock(&rwlp->rw_lock);
if (rv == 0) {
ASSERT(rwlp->rw_owner == NULL);
if (rw == RW_READER) {
ASSERT(rwlp->rw_count >= 0);
atomic_add_int(&rwlp->rw_count, 1);
} else {
ASSERT(rwlp->rw_count == 0);
rwlp->rw_count = -1;
rwlp->rw_owner = curthread;
}
return (1);
}
return (0);
}
/*ARGSUSED*/
int
rw_tryupgrade(krwlock_t *rwlp)
{
ASSERT(rwlp->rw_owner != (void *)-1UL);
return (0);
}
int
rw_lock_held(krwlock_t *rwlp)
{
return (rwlp->rw_count != 0);
}
/*
* =========================================================================
* condition variables
* =========================================================================
*/
/*ARGSUSED*/
void
cv_init(kcondvar_t *cv, char *name, int type, void *arg)
{
VERIFY(cond_init(cv, name, NULL) == 0);
}
void
cv_destroy(kcondvar_t *cv)
{
VERIFY(cond_destroy(cv) == 0);
}
void
cv_wait(kcondvar_t *cv, kmutex_t *mp)
{
ASSERT(mutex_owner(mp) == curthread);
mp->m_owner = NULL;
int ret = cond_wait(cv, &mp->m_lock);
VERIFY(ret == 0 || ret == EINTR);
mp->m_owner = curthread;
}
clock_t
cv_timedwait(kcondvar_t *cv, kmutex_t *mp, clock_t abstime)
{
int error;
struct timespec ts;
struct timeval tv;
clock_t delta;
ASSERT(abstime > 0);
top:
delta = abstime - lbolt;
if (delta <= 0)
return (-1);
if (gettimeofday(&tv, NULL) != 0)
assert(!"gettimeofday() failed");
ts.tv_sec = tv.tv_sec + delta / hz;
ts.tv_nsec = tv.tv_usec * 1000 + (delta % hz) * (NANOSEC / hz);
ASSERT(ts.tv_nsec >= 0);
if(ts.tv_nsec >= NANOSEC) {
ts.tv_sec++;
ts.tv_nsec -= NANOSEC;
}
ASSERT(mutex_owner(mp) == curthread);
mp->m_owner = NULL;
error = pthread_cond_timedwait(cv, &mp->m_lock, &ts);
mp->m_owner = curthread;
if (error == EINTR)
goto top;
if (error == ETIMEDOUT)
return (-1);
ASSERT(error == 0);
return (1);
}
void
cv_signal(kcondvar_t *cv)
{
VERIFY(cond_signal(cv) == 0);
}
void
cv_broadcast(kcondvar_t *cv)
{
VERIFY(cond_broadcast(cv) == 0);
}
/*
* =========================================================================
* vnode operations
* =========================================================================
*/
/*
* Note: for the xxxat() versions of these functions, we assume that the
* starting vp is always rootdir (which is true for spa_directory.c, the only
* ZFS consumer of these interfaces). We assert this is true, and then emulate
* them by adding '/' in front of the path.
*/
/*ARGSUSED*/
int
vn_open(char *path, int x1, int flags, int mode, vnode_t **vpp, int x2, int x3)
{
int fd;
vnode_t *vp;
int old_umask;
char realpath[MAXPATHLEN];
struct stat64 st;
/*
* If we're accessing a real disk from userland, we need to use
* the character interface to avoid caching. This is particularly
* important if we're trying to look at a real in-kernel storage
* pool from userland, e.g. via zdb, because otherwise we won't
* see the changes occurring under the segmap cache.
* On the other hand, the stupid character device returns zero
* for its size. So -- gag -- we open the block device to get
* its size, and remember it for subsequent VOP_GETATTR().
*/
if (strncmp(path, "/dev/", 5) == 0) {
char *dsk;
fd = open64(path, O_RDONLY);
if (fd == -1)
return (errno);
if (fstat64(fd, &st) == -1) {
close(fd);
return (errno);
}
close(fd);
(void) sprintf(realpath, "%s", path);
dsk = strstr(path, "/dsk/");
if (dsk != NULL)
(void) sprintf(realpath + (dsk - path) + 1, "r%s",
dsk + 1);
} else {
(void) sprintf(realpath, "%s", path);
if (!(flags & FCREAT) && stat64(realpath, &st) == -1)
return (errno);
}
if (flags & FCREAT)
old_umask = umask(0);
/*
* The construct 'flags - FREAD' conveniently maps combinations of
* FREAD and FWRITE to the corresponding O_RDONLY, O_WRONLY, and O_RDWR.
*/
fd = open64(realpath, flags - FREAD, mode);
if (flags & FCREAT)
(void) umask(old_umask);
if (fd == -1)
return (errno);
if (fstat64(fd, &st) == -1) {
close(fd);
return (errno);
}
(void) fcntl(fd, F_SETFD, FD_CLOEXEC);
*vpp = vp = umem_zalloc(sizeof (vnode_t), UMEM_NOFAIL);
vp->v_fd = fd;
vp->v_size = st.st_size;
vp->v_path = spa_strdup(path);
return (0);
}
int
vn_openat(char *path, int x1, int flags, int mode, vnode_t **vpp, int x2,
int x3, vnode_t *startvp)
{
char *realpath = umem_alloc(strlen(path) + 2, UMEM_NOFAIL);
int ret;
ASSERT(startvp == rootdir);
(void) sprintf(realpath, "/%s", path);
ret = vn_open(realpath, x1, flags, mode, vpp, x2, x3);
umem_free(realpath, strlen(path) + 2);
return (ret);
}
/*ARGSUSED*/
int
vn_rdwr(int uio, vnode_t *vp, void *addr, ssize_t len, offset_t offset,
int x1, int x2, rlim64_t x3, void *x4, ssize_t *residp)
{
ssize_t iolen, split;
if (uio == UIO_READ) {
iolen = pread64(vp->v_fd, addr, len, offset);
} else {
/*
* To simulate partial disk writes, we split writes into two
* system calls so that the process can be killed in between.
*/
split = (len > 0 ? rand() % len : 0);
iolen = pwrite64(vp->v_fd, addr, split, offset);
iolen += pwrite64(vp->v_fd, (char *)addr + split,
len - split, offset + split);
}
if (iolen == -1)
return (errno);
if (residp)
*residp = len - iolen;
else if (iolen != len)
return (EIO);
return (0);
}
void
vn_close(vnode_t *vp)
{
close(vp->v_fd);
spa_strfree(vp->v_path);
umem_free(vp, sizeof (vnode_t));
}
#ifdef ZFS_DEBUG
/*
* =========================================================================
* 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;
}
/*
* =========================================================================
* debug printfs
* =========================================================================
*/
void
__dprintf(const char *file, const char *func, int line, const char *fmt, ...)
{
const char *newfile;
va_list adx;
/*
* Get rid of annoying "../common/" prefix to filename.
*/
newfile = strrchr(file, '/');
if (newfile != NULL) {
newfile = newfile + 1; /* Get rid of leading / */
} else {
newfile = file;
}
if (dprintf_print_all ||
dprintf_find_string(newfile) ||
dprintf_find_string(func)) {
/* 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("%u ", thr_self());
#if 0
if (dprintf_find_string("cpu"))
(void) printf("%u ", getcpuid());
#endif
if (dprintf_find_string("time"))
(void) printf("%llu ", gethrtime());
if (dprintf_find_string("long"))
(void) printf("%s, line %d: ", newfile, line);
(void) printf("%s: ", func);
va_start(adx, fmt);
(void) vprintf(fmt, adx);
va_end(adx);
funlockfile(stdout);
}
}
#endif /* ZFS_DEBUG */
/*
* =========================================================================
* cmn_err() and panic()
* =========================================================================
*/
static char ce_prefix[CE_IGNORE][10] = { "", "NOTICE: ", "WARNING: ", "" };
static char ce_suffix[CE_IGNORE][2] = { "", "\n", "\n", "" };
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" */
}
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]);
}
}
/*PRINTFLIKE2*/
void
cmn_err(int ce, const char *fmt, ...)
{
va_list adx;
va_start(adx, fmt);
vcmn_err(ce, fmt, adx);
va_end(adx);
}
/*
* =========================================================================
* kobj interfaces
* =========================================================================
*/
struct _buf *
kobj_open_file(char *name)
{
struct _buf *file;
vnode_t *vp;
/* set vp as the _fd field of the file */
if (vn_openat(name, UIO_SYSSPACE, FREAD, 0, &vp, 0, 0, rootdir) != 0)
return ((void *)-1UL);
file = umem_zalloc(sizeof (struct _buf), UMEM_NOFAIL);
file->_fd = (intptr_t)vp;
return (file);
}
int
kobj_read_file(struct _buf *file, char *buf, unsigned size, unsigned off)
{
ssize_t resid;
vn_rdwr(UIO_READ, (vnode_t *)file->_fd, buf, size, (offset_t)off,
UIO_SYSSPACE, 0, 0, 0, &resid);
return (size - resid);
}
void
kobj_close_file(struct _buf *file)
{
vn_close((vnode_t *)file->_fd);
umem_free(file, sizeof (struct _buf));
}
int
kobj_get_filesize(struct _buf *file, uint64_t *size)
{
struct stat64 st;
vnode_t *vp = (vnode_t *)file->_fd;
if (fstat64(vp->v_fd, &st) == -1) {
vn_close(vp);
return (errno);
}
*size = st.st_size;
return (0);
}
/*
* =========================================================================
* misc routines
* =========================================================================
*/
void
delay(clock_t ticks)
{
poll(0, 0, ticks * (1000 / hz));
}
#if 0
/*
* Find highest one bit set.
* Returns bit number + 1 of highest bit that is set, otherwise returns 0.
* High order bit is 31 (or 63 in _LP64 kernel).
*/
int
highbit(ulong_t i)
{
register int h = 1;
if (i == 0)
return (0);
#ifdef _LP64
if (i & 0xffffffff00000000ul) {
h += 32; i >>= 32;
}
#endif
if (i & 0xffff0000) {
h += 16; i >>= 16;
}
if (i & 0xff00) {
h += 8; i >>= 8;
}
if (i & 0xf0) {
h += 4; i >>= 4;
}
if (i & 0xc) {
h += 2; i >>= 2;
}
if (i & 0x2) {
h += 1;
}
return (h);
}
#endif
static int
random_get_bytes_common(uint8_t *ptr, size_t len, char *devname)
{
int fd = open(devname, O_RDONLY);
size_t resid = len;
ssize_t bytes;
ASSERT(fd != -1);
while (resid != 0) {
bytes = read(fd, ptr, resid);
ASSERT(bytes >= 0);
ptr += bytes;
resid -= bytes;
}
close(fd);
return (0);
}
int
random_get_bytes(uint8_t *ptr, size_t len)
{
return (random_get_bytes_common(ptr, len, "/dev/random"));
}
int
random_get_pseudo_bytes(uint8_t *ptr, size_t len)
{
return (random_get_bytes_common(ptr, len, "/dev/urandom"));
}
int
ddi_strtoul(const char *hw_serial, char **nptr, int base, unsigned long *result)
{
char *end;
*result = strtoul(hw_serial, &end, base);
if (*result == 0)
return (errno);
return (0);
}
/*
* =========================================================================
* kernel emulation setup & teardown
* =========================================================================
*/
static int
umem_out_of_memory(void)
{
char errmsg[] = "out of memory -- generating core dump\n";
write(fileno(stderr), errmsg, sizeof (errmsg));
abort();
return (0);
}
void
kernel_init(int mode)
{
umem_nofail_callback(umem_out_of_memory);
physmem = sysconf(_SC_PHYS_PAGES);
dprintf("physmem = %llu pages (%.2f GB)\n", physmem,
(double)physmem * sysconf(_SC_PAGE_SIZE) / (1ULL << 30));
snprintf(hw_serial, sizeof (hw_serial), "%ld", gethostid());
spa_init(mode);
}
void
kernel_fini(void)
{
spa_fini();
}
int
z_uncompress(void *dst, size_t *dstlen, const void *src, size_t srclen)
{
int ret;
uLongf len = *dstlen;
if ((ret = uncompress(dst, &len, src, srclen)) == Z_OK)
*dstlen = (size_t)len;
return (ret);
}
int
z_compress_level(void *dst, size_t *dstlen, const void *src, size_t srclen,
int level)
{
int ret;
uLongf len = *dstlen;
if ((ret = compress2(dst, &len, src, srclen, level)) == Z_OK)
*dstlen = (size_t)len;
return (ret);
}
|