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
|
/*
* Ldisc rw semaphore
*
* The ldisc semaphore is semantically a rw_semaphore but which enforces
* an alternate policy, namely:
* 1) Supports lock wait timeouts
* 2) Write waiter has priority
* 3) Downgrading is not supported
*
* Implementation notes:
* 1) Upper half of semaphore count is a wait count (differs from rwsem
* in that rwsem normalizes the upper half to the wait bias)
* 2) Lacks overflow checking
*
* The generic counting was copied and modified from include/asm-generic/rwsem.h
* by Paul Mackerras <paulus@samba.org>.
*
* The scheduling policy was copied and modified from lib/rwsem.c
* Written by David Howells (dhowells@redhat.com).
*
* This implementation incorporates the write lock stealing work of
* Michel Lespinasse <walken@google.com>.
*
* Copyright (C) 2013 Peter Hurley <peter@hurleysoftware.com>
*
* This file may be redistributed under the terms of the GNU General Public
* License v2.
*/
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/tty.h>
#include <linux/sched.h>
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define __acq(l, s, t, r, c, n, i) \
lock_acquire(&(l)->dep_map, s, t, r, c, n, i)
# define __rel(l, n, i) \
lock_release(&(l)->dep_map, n, i)
# ifdef CONFIG_PROVE_LOCKING
# define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 2, NULL, i)
# define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 2, n, i)
# define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 2, NULL, i)
# define lockdep_release(l, n, i) __rel(l, n, i)
# else
# define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 1, NULL, i)
# define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 1, n, i)
# define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 1, NULL, i)
# define lockdep_release(l, n, i) __rel(l, n, i)
# endif
#else
# define lockdep_acquire(l, s, t, i) do { } while (0)
# define lockdep_acquire_nest(l, s, t, n, i) do { } while (0)
# define lockdep_acquire_read(l, s, t, i) do { } while (0)
# define lockdep_release(l, n, i) do { } while (0)
#endif
#ifdef CONFIG_LOCK_STAT
# define lock_stat(_lock, stat) lock_##stat(&(_lock)->dep_map, _RET_IP_)
#else
# define lock_stat(_lock, stat) do { } while (0)
#endif
#if BITS_PER_LONG == 64
# define LDSEM_ACTIVE_MASK 0xffffffffL
#else
# define LDSEM_ACTIVE_MASK 0x0000ffffL
#endif
#define LDSEM_UNLOCKED 0L
#define LDSEM_ACTIVE_BIAS 1L
#define LDSEM_WAIT_BIAS (-LDSEM_ACTIVE_MASK-1)
#define LDSEM_READ_BIAS LDSEM_ACTIVE_BIAS
#define LDSEM_WRITE_BIAS (LDSEM_WAIT_BIAS + LDSEM_ACTIVE_BIAS)
struct ldsem_waiter {
struct list_head list;
struct task_struct *task;
};
static inline long ldsem_atomic_update(long delta, struct ld_semaphore *sem)
{
return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
}
static inline int ldsem_cmpxchg(long *old, long new, struct ld_semaphore *sem)
{
long tmp = *old;
*old = atomic_long_cmpxchg(&sem->count, *old, new);
return *old == tmp;
}
/*
* Initialize an ldsem:
*/
void __init_ldsem(struct ld_semaphore *sem, const char *name,
struct lock_class_key *key)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* Make sure we are not reinitializing a held semaphore:
*/
debug_check_no_locks_freed((void *)sem, sizeof(*sem));
lockdep_init_map(&sem->dep_map, name, key, 0);
#endif
sem->count = LDSEM_UNLOCKED;
sem->wait_readers = 0;
raw_spin_lock_init(&sem->wait_lock);
INIT_LIST_HEAD(&sem->read_wait);
INIT_LIST_HEAD(&sem->write_wait);
}
static void __ldsem_wake_readers(struct ld_semaphore *sem)
{
struct ldsem_waiter *waiter, *next;
struct task_struct *tsk;
long adjust, count;
/* Try to grant read locks to all readers on the read wait list.
* Note the 'active part' of the count is incremented by
* the number of readers before waking any processes up.
*/
adjust = sem->wait_readers * (LDSEM_ACTIVE_BIAS - LDSEM_WAIT_BIAS);
count = ldsem_atomic_update(adjust, sem);
do {
if (count > 0)
break;
if (ldsem_cmpxchg(&count, count - adjust, sem))
return;
} while (1);
list_for_each_entry_safe(waiter, next, &sem->read_wait, list) {
tsk = waiter->task;
smp_mb();
waiter->task = NULL;
wake_up_process(tsk);
put_task_struct(tsk);
}
INIT_LIST_HEAD(&sem->read_wait);
sem->wait_readers = 0;
}
static inline int writer_trylock(struct ld_semaphore *sem)
{
/* only wake this writer if the active part of the count can be
* transitioned from 0 -> 1
*/
long count = ldsem_atomic_update(LDSEM_ACTIVE_BIAS, sem);
do {
if ((count & LDSEM_ACTIVE_MASK) == LDSEM_ACTIVE_BIAS)
return 1;
if (ldsem_cmpxchg(&count, count - LDSEM_ACTIVE_BIAS, sem))
return 0;
} while (1);
}
static void __ldsem_wake_writer(struct ld_semaphore *sem)
{
struct ldsem_waiter *waiter;
waiter = list_entry(sem->write_wait.next, struct ldsem_waiter, list);
wake_up_process(waiter->task);
}
/*
* handle the lock release when processes blocked on it that can now run
* - if we come here from up_xxxx(), then:
* - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
* - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
* - the spinlock must be held by the caller
* - woken process blocks are discarded from the list after having task zeroed
*/
static void __ldsem_wake(struct ld_semaphore *sem)
{
if (!list_empty(&sem->write_wait))
__ldsem_wake_writer(sem);
else if (!list_empty(&sem->read_wait))
__ldsem_wake_readers(sem);
}
static void ldsem_wake(struct ld_semaphore *sem)
{
unsigned long flags;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
__ldsem_wake(sem);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}
/*
* wait for the read lock to be granted
*/
static struct ld_semaphore __sched *
down_read_failed(struct ld_semaphore *sem, long count, long timeout)
{
struct ldsem_waiter waiter;
struct task_struct *tsk = current;
long adjust = -LDSEM_ACTIVE_BIAS + LDSEM_WAIT_BIAS;
/* set up my own style of waitqueue */
raw_spin_lock_irq(&sem->wait_lock);
/* Try to reverse the lock attempt but if the count has changed
* so that reversing fails, check if there are are no waiters,
* and early-out if not */
do {
if (ldsem_cmpxchg(&count, count + adjust, sem))
break;
if (count > 0) {
raw_spin_unlock_irq(&sem->wait_lock);
return sem;
}
} while (1);
list_add_tail(&waiter.list, &sem->read_wait);
sem->wait_readers++;
waiter.task = tsk;
get_task_struct(tsk);
/* if there are no active locks, wake the new lock owner(s) */
if ((count & LDSEM_ACTIVE_MASK) == 0)
__ldsem_wake(sem);
raw_spin_unlock_irq(&sem->wait_lock);
/* wait to be given the lock */
for (;;) {
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
if (!waiter.task)
break;
if (!timeout)
break;
timeout = schedule_timeout(timeout);
}
__set_task_state(tsk, TASK_RUNNING);
if (!timeout) {
/* lock timed out but check if this task was just
* granted lock ownership - if so, pretend there
* was no timeout; otherwise, cleanup lock wait */
raw_spin_lock_irq(&sem->wait_lock);
if (waiter.task) {
ldsem_atomic_update(-LDSEM_WAIT_BIAS, sem);
list_del(&waiter.list);
raw_spin_unlock_irq(&sem->wait_lock);
put_task_struct(waiter.task);
return NULL;
}
raw_spin_unlock_irq(&sem->wait_lock);
}
return sem;
}
/*
* wait for the write lock to be granted
*/
static struct ld_semaphore __sched *
down_write_failed(struct ld_semaphore *sem, long count, long timeout)
{
struct ldsem_waiter waiter;
struct task_struct *tsk = current;
long adjust = -LDSEM_ACTIVE_BIAS;
int locked = 0;
/* set up my own style of waitqueue */
raw_spin_lock_irq(&sem->wait_lock);
/* Try to reverse the lock attempt but if the count has changed
* so that reversing fails, check if the lock is now owned,
* and early-out if so */
do {
if (ldsem_cmpxchg(&count, count + adjust, sem))
break;
if ((count & LDSEM_ACTIVE_MASK) == LDSEM_ACTIVE_BIAS) {
raw_spin_unlock_irq(&sem->wait_lock);
return sem;
}
} while (1);
list_add_tail(&waiter.list, &sem->write_wait);
waiter.task = tsk;
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
for (;;) {
if (!timeout)
break;
raw_spin_unlock_irq(&sem->wait_lock);
timeout = schedule_timeout(timeout);
raw_spin_lock_irq(&sem->wait_lock);
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
if ((locked = writer_trylock(sem)))
break;
}
if (!locked)
ldsem_atomic_update(-LDSEM_WAIT_BIAS, sem);
list_del(&waiter.list);
raw_spin_unlock_irq(&sem->wait_lock);
__set_task_state(tsk, TASK_RUNNING);
/* lock wait may have timed out */
<
|