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
|
/*
* Copyright (c) 1995
* The Regents of the University of California. All rights reserved.
*
* Copyright (C) 1997
* John S. Dyson. All rights reserved.
*
* This code contains ideas from software contributed to Berkeley by
* Avadis Tevanian, Jr., Michael Wayne Young, and the Mach Operating
* System project at Carnegie-Mellon University.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)kern_lock.c 8.18 (Berkeley) 5/21/95
* $FreeBSD$
*/
#include <sys/param.h>
#include <sys/proc.h>
#include <sys/kernel.h>
#include <sys/ktr.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
#include <sys/systm.h>
/*
* Locking primitives implementation.
* Locks provide shared/exclusive sychronization.
*/
#define LOCK_WAIT_TIME 100
#define LOCK_SAMPLE_WAIT 7
#if defined(DIAGNOSTIC)
#define LOCK_INLINE
#else
#define LOCK_INLINE __inline
#endif
#define LK_ALL (LK_HAVE_EXCL | LK_WANT_EXCL | LK_WANT_UPGRADE | \
LK_SHARE_NONZERO | LK_WAIT_NONZERO)
/*
* Mutex array variables. Rather than each lockmgr lock having its own mutex,
* share a fixed (at boot time) number of mutexes across all lockmgr locks in
* order to keep sizeof(struct lock) down.
*/
int lock_mtx_valid;
static struct mtx lock_mtx;
static int acquire(struct lock *lkp, int extflags, int wanted);
static int apause(struct lock *lkp, int flags);
static int acquiredrain(struct lock *lkp, int extflags) ;
static void
lockmgr_init(void *dummy __unused)
{
/*
* Initialize the lockmgr protection mutex if it hasn't already been
* done. Unless something changes about kernel startup order, VM
* initialization will always cause this mutex to already be
* initialized in a call to lockinit().
*/
if (lock_mtx_valid == 0) {
mtx_init(&lock_mtx, "lockmgr", MTX_DEF);
lock_mtx_valid = 1;
}
}
SYSINIT(lmgrinit, SI_SUB_LOCK, SI_ORDER_FIRST, lockmgr_init, NULL)
static LOCK_INLINE void
sharelock(struct lock *lkp, int incr) {
lkp->lk_flags |= LK_SHARE_NONZERO;
lkp->lk_sharecount += incr;
}
static LOCK_INLINE void
shareunlock(struct lock *lkp, int decr) {
KASSERT(lkp->lk_sharecount >= decr, ("shareunlock: count < decr"));
if (lkp->lk_sharecount == decr) {
lkp->lk_flags &= ~LK_SHARE_NONZERO;
if (lkp->lk_flags & (LK_WANT_UPGRADE | LK_WANT_EXCL)) {
wakeup(lkp);
}
lkp->lk_sharecount = 0;
} else {
lkp->lk_sharecount -= decr;
}
}
/*
* This is the waitloop optimization.
*/
static int
apause(struct lock *lkp, int flags)
{
#ifdef SMP
int i, lock_wait;
#endif
if ((lkp->lk_flags & flags) == 0)
return 0;
#ifdef SMP
for (lock_wait = LOCK_WAIT_TIME; lock_wait > 0; lock_wait--) {
mtx_unlock(lkp->lk_interlock);
for (i = LOCK_SAMPLE_WAIT; i > 0; i--)
if ((lkp->lk_flags & flags) == 0)
break;
mtx_lock(lkp->lk_interlock);
if ((lkp->lk_flags & flags) == 0)
return 0;
}
#endif
return 1;
}
static int
acquire(struct lock *lkp, int extflags, int wanted) {
int s, error;
CTR3(KTR_LOCKMGR,
"acquire(): lkp == %p, extflags == 0x%x, wanted == 0x%x\n",
lkp, extflags, wanted);
if ((extflags & LK_NOWAIT) && (lkp->lk_flags & wanted)) {
return EBUSY;
}
if (((lkp->lk_flags | extflags) & LK_NOPAUSE) == 0) {
error = apause(lkp, wanted);
if (error == 0)
return 0;
}
s = splhigh();
while ((lkp->lk_flags & wanted) != 0) {
lkp->lk_flags |= LK_WAIT_NONZERO;
lkp->lk_waitcount++;
error = msleep(lkp, lkp->lk_interlock, lkp->lk_prio,
lkp->lk_wmesg,
((extflags & LK_TIMELOCK) ? lkp->lk_timo : 0));
if (lkp->lk_waitcount == 1) {
lkp->lk_flags &= ~LK_WAIT_NONZERO;
lkp->lk_waitcount = 0;
} else {
lkp->lk_waitcount--;
}
if (error) {
splx(s);
return error;
}
if (extflags & LK_SLEEPFAIL) {
splx(s);
return ENOLCK;
}
}
splx(s);
return 0;
}
/*
* Set, change, or release a lock.
*
* Shared requests increment the shared count. Exclusive requests set the
* LK_WANT_EXCL flag (preventing further shared locks), and wait for already
* accepted shared locks and shared-to-exclusive upgrades to go away.
*/
int
#ifndef DEBUG_LOCKS
lockmgr(lkp, flags, interlkp, td)
#else
debuglockmgr(lkp, flags, interlkp, td, name, file, line)
#endif
struct lock *lkp;
u_int flags;
struct mtx *interlkp;
struct thread *td;
#ifdef DEBUG_LOCKS
const char *name; /* Name of lock function */
const char *file; /* Name of file call is from */
int line; /* Line number in file */
#endif
{
int error;
pid_t pid;
int extflags, lockflags;
CTR5(KTR_LOCKMGR,
"lockmgr(): lkp == %p (lk_wmesg == \"%s\"), flags == 0x%x, "
"interlkp == %p, td == %p", lkp, lkp->lk_wmesg, flags, interlkp, td);
error = 0;
if (td == NULL)
pid = LK_KERNPROC;
else
pid = td->td_proc->p_pid;
mtx_lock(lkp->lk_interlock);
if (flags & LK_INTERLOCK) {
mtx_assert(interlkp, MA_OWNED | MA_NOTRECURSED);
mtx_unlock(interlkp);
}
if (panicstr != NULL) {
mtx_unlock(lkp->lk_interlock);
return (0);
}
extflags = (flags | lkp->lk_flags) & LK_EXTFLG_MASK;
switch (flags & LK_TYPE_MASK) {
case LK_SHARED:
/*
* If we are not the exclusive lock holder, we have to block
* while there is an exclusive lock holder or while an
* exclusive lock request or upgrade request is in progress.
*
* However, if TDF_DEADLKTREAT is set, we override exclusive
* lock requests or upgrade requests ( but not the exclusive
* lock itself ).
*/
if (lkp->lk_lockholder != pid) {
lockflags = LK_HAVE_EXCL;
mtx_lock_spin(&sched_lock);
if (td != NULL && !(td->td_flags & TDF_DEADLKTREAT))
lockflags |= LK_WANT_EXCL | LK_WANT_UPGRADE;
mtx_unlock_spin(&sched_lock);
error = acquire(lkp, extflags, lockflags);
if (error)
break;
sharelock(lkp, 1);
break;
}
/*
* We hold an exclusive lock, so downgrade it to shared.
* An alternative would be to fail with EDEADLK.
*/
sharelock(lkp, 1);
/* fall into downgrade */
case LK_DOWNGRADE:
KASSERT(lkp->lk_lockholder == pid && lkp->lk_exclusivecount != 0,
("lockmgr: not holding exclusive lock "
"(owner pid (%d) != pid (%d), exlcnt (%d) != 0",
lkp->lk_lockholder, pid, lkp->lk_exclusivecount));
sharelock(lkp, lkp->lk_exclusivecount);
lkp->lk_exclusivecount = 0;
lkp->lk_flags &= ~LK_HAVE_EXCL;
lkp->lk_lockholder = LK_NOPROC;
if (lkp->lk_waitcount)
wakeup((void *)lkp);
break;
case LK_EXCLUPGRADE:
/*
* If another process is ahead of us to get an upgrade,
* then we want to fail rather than have an intervening
* exclusive access.
*/
if (lkp->lk_flags & LK_WANT_UPGRADE) {
shareunlock(lkp, 1);
error = EBUSY;
break;
}
/* fall into normal upgrade */
case LK_UPGRADE:
/*
* Upgrade a shared lock to an exclusive one. If another
* shared lock has already requested an upgrade to an
* exclusive lock, our shared lock is released and an
* exclusive lock is requested (which will be granted
* after the upgrade). If we return an error, the file
* will always be unlocked.
*/
if ((lkp->lk_lockholder == pid) || (lkp->lk_sharecount <= 0))
panic("lockmgr: upgrade exclusive lock");
shareunlock(lkp, 1);
/*
* If we are just polling, check to see if we will block.
*/
if ((extflags & LK_NOWAIT) &&
((lkp->lk_flags & LK_WANT_UPGRADE) ||
lkp->lk_sharecount > 1)) {
error = EBUSY;
break;
}
if ((lkp->lk_flags & LK_WANT_UPGRADE) == 0) {
/*
* We are first shared lock to request an upgrade, so
* request upgrade and wait for the shared count to
* drop to zero, then take exclusive lock.
*/
lkp->lk_flags |= LK_WANT_UPGRADE;
error = acquire(lkp, extflags, LK_SHARE_NONZERO);
lkp->lk_flags &= ~LK_WANT_UPGRADE;
if (error)
break;
lkp->lk_flags |= LK_HAVE_EXCL;
lkp->lk_lockholder = pid;
if (lkp->lk_exclusivecount != 0)
panic("lockmgr: non-zero exclusive count");
lkp->lk_exclusivecount = 1;
#if defined(DEBUG_LOCKS)
lkp->lk_filename = file;
lkp->lk_lineno = line;
lkp->lk_lockername = name;
#endif
break;
}
/*
* Someone else has requested upgrade. Release our shared
* lock, awaken upgrade requestor if we are the last shared
* lock, then request an exclusive lock.
*/
if ( (lkp->lk_flags & (LK_SHARE_NONZERO|LK_WAIT_NONZERO)) ==
LK_WAIT_NONZERO)
wakeup((void *)lkp);
/* fall into exclusive request */
case LK_EXCLUSIVE:
if (lkp->lk_lockholder == pid && pid != LK_KERNPROC) {
/*
* Recursive lock.
*/
if ((extflags & (LK_NOWAIT | LK_CANRECURSE)) == 0)
panic("lockmgr: locking against myself");
if ((extflags & LK_CANRECURSE) != 0) {
lkp->lk_exclusivecount++;
break;
}
}
/*
* If we are just polling, check to see if we will sleep.
*/
if ((extflags & LK_NOWAIT) &&
(lkp->lk_flags & (LK_HAVE_EXCL | LK_WANT_EXCL | LK_WANT_UPGRADE | LK_SHARE_NONZERO))) {
error = EBUSY;
break;
}
/*
* Try to acquire the want_exclusive flag.
*/
error = acquire(lkp, extflags, (LK_HAVE_EXCL | LK_WANT_EXCL));
if (error)
break;
lkp->lk_flags |= LK_WANT_EXCL;
/*
* Wait for shared locks and upgrades to finish.
*/
error = acquire(lkp, extflags, LK_WANT_UPGRADE | LK_SHARE_NONZERO);
lkp->lk_flags &= ~LK_WANT_EXCL;
if (error)
break;
lkp->lk_flags |= LK_HAVE_EXCL;
lkp->lk_lockholder = pid;
if (lkp->lk_exclusivecount != 0)
panic("lockmgr: non-zero exclusive count");
lkp->lk_exclusivecount = 1;
#if defined(DEBUG_LOCKS)
lkp->lk_filename = file;
lkp->lk_lineno = line;
lkp->lk_lockername = name;
#endif
break;
case LK_RELEASE:
if (lkp->lk_exclusivecount != 0) {
if (lkp->lk_lockholder != pid &&
lkp->lk_lockholder != LK_KERNPROC) {
panic("lockmgr: pid %d, not %s %d unlocking",
pid, "exclusive lock holder",
lkp->lk_lockholder);
}
if (lkp->lk_exclusivecount == 1) {
lkp->lk_flags &= ~LK_HAVE_EXCL;
lkp->lk_lockholder = LK_NOPROC;
lkp->lk_exclusivecount = 0;
} else {
lkp->lk_exclusivecount--;
}
} else if (lkp->lk_flags & LK_SHARE_NONZERO)
shareunlock(lkp, 1);
if (lkp->lk_flags & LK_WAIT_NONZERO)
wakeup((void *)lkp);
break;
case LK_DRAIN:
/*
* Check that we do not already hold the lock, as it can
* never drain if we do. Unfortunately, we have no way to
* check for holding a shared lock, but at least we can
* check for an exclusive one.
*/
if (lkp->lk_lockholder == pid)
panic("lockmgr: draining against myself");
error = acquiredrain(lkp, extflags);
if (error)
break;
lkp->lk_flags |= LK_DRAINING | LK_HAVE_EXCL;
lkp->lk_lockholder = pid;
lkp->lk_exclusivecount = 1;
#if defined(DEBUG_LOCKS)
lkp->lk_filename = file;
lkp->lk_lineno = line;
lkp->lk_lockername = name;
#endif
break;
default:
mtx_unlock(lkp->lk_interlock);
panic("lockmgr: unknown locktype request %d",
flags & LK_TYPE_MASK);
/* NOTREACHED */
}
if ((lkp->lk_flags & LK_WAITDRAIN) &&
(lkp->lk_flags & (LK_HAVE_EXCL | LK_WANT_EXCL | LK_WANT_UPGRADE |
LK_SHARE_NONZERO | LK_WAIT_NONZERO)) == 0) {
lkp->lk_flags &= ~LK_WAITDRAIN;
wakeup((void *)&lkp->lk_flags);
}
mtx_unlock(lkp->lk_interlock);
return (error);
}
static int
acquiredrain(struct lock *lkp, int extflags) {
int error;
if ((extflags & LK_NOWAIT) && (lkp->lk_flags & LK_ALL)) {
return EBUSY;
}
error = apause(lkp, LK_ALL);
if (error == 0)
return 0;
while (lkp->lk_flags & LK_ALL) {
lkp->lk_flags |= LK_WAITDRAIN;
error = msleep(&lkp->lk_flags, lkp->lk_interlock, lkp->lk_prio,
lkp->lk_wmesg,
((extflags & LK_TIMELOCK) ? lkp->lk_timo : 0));
if (error)
return error;
if (extflags & LK_SLEEPFAIL) {
return ENOLCK;
}
}
return 0;
}
/*
* Initialize a lock; required before use.
*/
void
lockinit(lkp, prio, wmesg, timo, flags)
struct lock *lkp;
int prio;
const char *wmesg;
int timo;
int flags;
{
CTR5(KTR_LOCKMGR, "lockinit(): lkp == %p, prio == %d, wmesg == \"%s\", "
"timo == %d, flags = 0x%x\n", lkp, prio, wmesg, timo, flags);
if (lock_mtx_valid == 0) {
mtx_init(&lock_mtx, "lockmgr", MTX_DEF);
lock_mtx_valid = 1;
}
/*
* XXX cleanup - make sure mtxpool is always initialized before
* this is ever called.
*/
if (mtx_pool_valid) {
mtx_lock(&lock_mtx);
lkp->lk_interlock = mtx_pool_alloc();
mtx_unlock(&lock_mtx);
} else {
lkp->lk_interlock = &lock_mtx;
}
lkp->lk_flags = (flags & LK_EXTFLG_MASK);
lkp->lk_sharecount = 0;
lkp->lk_waitcount = 0;
lkp->lk_exclusivecount = 0;
lkp->lk_prio = prio;
lkp->lk_wmesg = wmesg;
lkp->lk_timo = timo;
lkp->lk_lockholder = LK_NOPROC;
}
/*
* Destroy a lock.
*/
void
lockdestroy(lkp)
struct lock *lkp;
{
CTR2(KTR_LOCKMGR, "lockdestroy(): lkp == %p (lk_wmesg == \"%s\")",
lkp, lkp->lk_wmesg);
}
/*
* Determine the status of a lock.
*/
int
lockstatus(lkp, td)
struct lock *lkp;
struct thread *td;
{
int lock_type = 0;
mtx_lock(lkp->lk_interlock);
if (lkp->lk_exclusivecount != 0) {
if (td == NULL || lkp->lk_lockholder == td->td_proc->p_pid)
lock_type = LK_EXCLUSIVE;
else
lock_type = LK_EXCLOTHER;
} else if (lkp->lk_sharecount != 0)
lock_type = LK_SHARED;
mtx_unlock(lkp->lk_interlock);
return (lock_type);
}
/*
* Determine the number of holders of a lock.
*/
int
lockcount(lkp)
struct lock *lkp;
{
int count;
mtx_lock(lkp->lk_interlock);
count = lkp->lk_exclusivecount + lkp->lk_sharecount;
mtx_unlock(lkp->lk_interlock);
return (count);
}
/*
* Print out information about state of a lock. Used by VOP_PRINT
* routines to display status about contained locks.
*/
void
lockmgr_printinfo(lkp)
struct lock *lkp;
{
if (lkp->lk_sharecount)
printf(" lock type %s: SHARED (count %d)", lkp->lk_wmesg,
lkp->lk_sharecount);
else if (lkp->lk_flags & LK_HAVE_EXCL)
printf(" lock type %s: EXCL (count %d) by pid %d",
lkp->lk_wmesg, lkp->lk_exclusivecount, lkp->lk_lockholder);
if (lkp->lk_waitcount > 0)
printf(" with %d pending", lkp->lk_waitcount);
}
|