aboutsummaryrefslogtreecommitdiff
path: root/kernel/locking/rwsem-xadd.c
blob: a4d4de05b2d16707becf6179f8ae2ebed334bead (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
/* rwsem.c: R/W semaphores: contention handling functions
 *
 * Written by David Howells (dhowells@redhat.com).
 * Derived from arch/i386/kernel/semaphore.c
 *
 * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
 * and Michel Lespinasse <walken@google.com>
 *
 * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
 * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
 */
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/sched/rt.h>
#include <linux/osq_lock.h>

#include "rwsem.h"

/*
 * Guide to the rw_semaphore's count field for common values.
 * (32-bit case illustrated, similar for 64-bit)
 *
 * 0x0000000X	(1) X readers active or attempting lock, no writer waiting
 *		    X = #active_readers + #readers attempting to lock
 *		    (X*ACTIVE_BIAS)
 *
 * 0x00000000	rwsem is unlocked, and no one is waiting for the lock or
 *		attempting to read lock or write lock.
 *
 * 0xffff000X	(1) X readers active or attempting lock, with waiters for lock
 *		    X = #active readers + # readers attempting lock
 *		    (X*ACTIVE_BIAS + WAITING_BIAS)
 *		(2) 1 writer attempting lock, no waiters for lock
 *		    X-1 = #active readers + #readers attempting lock
 *		    ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
 *		(3) 1 writer active, no waiters for lock
 *		    X-1 = #active readers + #readers attempting lock
 *		    ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
 *
 * 0xffff0001	(1) 1 reader active or attempting lock, waiters for lock
 *		    (WAITING_BIAS + ACTIVE_BIAS)
 *		(2) 1 writer active or attempting lock, no waiters for lock
 *		    (ACTIVE_WRITE_BIAS)
 *
 * 0xffff0000	(1) There are writers or readers queued but none active
 *		    or in the process of attempting lock.
 *		    (WAITING_BIAS)
 *		Note: writer can attempt to steal lock for this count by adding
 *		ACTIVE_WRITE_BIAS in cmpxchg and checking the old count
 *
 * 0xfffe0001	(1) 1 writer active, or attempting lock. Waiters on queue.
 *		    (ACTIVE_WRITE_BIAS + WAITING_BIAS)
 *
 * Note: Readers attempt to lock by adding ACTIVE_BIAS in down_read and checking
 *	 the count becomes more than 0 for successful lock acquisition,
 *	 i.e. the case where there are only readers or nobody has lock.
 *	 (1st and 2nd case above).
 *
 *	 Writers attempt to lock by adding ACTIVE_WRITE_BIAS in down_write and
 *	 checking the count becomes ACTIVE_WRITE_BIAS for successful lock
 *	 acquisition (i.e. nobody else has lock or attempts lock).  If
 *	 unsuccessful, in rwsem_down_write_failed, we'll check to see if there
 *	 are only waiters but none active (5th case above), and attempt to
 *	 steal the lock.
 *
 */

/*
 * Initialize an rwsem:
 */
void __init_rwsem(struct rw_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 = RWSEM_UNLOCKED_VALUE;
	raw_spin_lock_init(&sem->wait_lock);
	INIT_LIST_HEAD(&sem->wait_list);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
	sem->owner = NULL;
	osq_lock_init(&sem->osq);
#endif
}

EXPORT_SYMBOL(__init_rwsem);

enum rwsem_waiter_type {
	RWSEM_WAITING_FOR_WRITE,
	RWSEM_WAITING_FOR_READ
};

struct rwsem_waiter {
	struct list_head list;
	struct task_struct *task;
	enum rwsem_waiter_type type;
};

enum rwsem_wake_type {
	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
	RWSEM_WAKE_READERS,	/* Wake readers only */
	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
};

/*
 * 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)
 * - there must be someone on the queue
 * - the spinlock must be held by the caller
 * - woken process blocks are discarded from the list after having task zeroed
 * - writers are only woken if downgrading is false
 */
static struct rw_semaphore *
__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
{
	struct rwsem_waiter *waiter;
	struct task_struct *tsk;
	struct list_head *next;
	long oldcount, woken, loop, adjustment;

	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
		if (wake_type == RWSEM_WAKE_ANY)
			/* Wake writer at the front of the queue, but do not
			 * grant it the lock yet as we want other writers
			 * to be able to steal it.  Readers, on the other hand,
			 * will block as they will notice the queued writer.
			 */
			wake_up_process(waiter->task);
		goto out;
	}

	/* Writers might steal the lock before we grant it to the next reader.
	 * We prefer to do the first reader grant before counting readers
	 * so we can bail out early if a writer stole the lock.
	 */
	adjustment = 0;
	if (wake_type != RWSEM_WAKE_READ_OWNED) {
		adjustment = RWSEM_ACTIVE_READ_BIAS;
 try_reader_grant:
		oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
			/* A writer stole the lock. Undo our reader grant. */
			if (rwsem_atomic_update(-adjustment, sem) &
						RWSEM_ACTIVE_MASK)
				goto out;
			/* Last active locker left. Retry waking readers. */
			goto try_reader_grant;
		}
	}

	/* Grant an infinite number of read locks to the readers at the front
	 * of the queue.  Note we increment the 'active part' of the count by
	 * the number of readers before waking any processes up.
	 */
	woken = 0;
	do {
		woken++;

		if (waiter->list.next == &sem->wait_list)
			break;

		waiter = list_entry(waiter->list.next,
					struct rwsem_waiter, list);

	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);

	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
	if (waiter->type != RWSEM_WAITING_FOR_WRITE)
		/* hit end of list above */
		adjustment -= RWSEM_WAITING_BIAS;

	if (adjustment)
		rwsem_atomic_add(adjustment, sem);

	next = sem->wait_list.next;
	loop = woken;
	do {
		waiter = list_entry(next, struct rwsem_waiter, list);
		next = waiter->list.next;
		tsk = waiter->task;
		/*
		 * Make sure we do not wakeup the next reader before
		 * setting the nil condition to grant the next reader;
		 * otherwise we could miss the wakeup on the other
		 * side and end up sleeping again. See the pairing
		 * in rwsem_down_read_failed().
		 */
		smp_mb();
		waiter->task = NULL;
		wake_up_process(tsk);
		put_task_struct(tsk);
	} while (--loop);

	sem->wait_list.next = next;
	next->prev = &sem->wait_list;

 out:
	return sem;
}

/*
 * Wait for the read lock to be granted
 */
__visible
struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
{
	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
	struct rwsem_waiter waiter;
	struct task_struct *tsk = current;

	/* set up my own style of waitqueue */
	waiter.task = tsk;
	waiter.type = RWSEM_WAITING_FOR_READ;
	get_task_struct(tsk);

	raw_spin_lock_irq(&sem->wait_lock);
	if (list_empty(&sem->wait_list))
		adjustment += RWSEM_WAITING_BIAS;
	list_add_tail(&waiter.list, &sem->wait_list);

	/* we're now waiting on the lock, but no longer actively locking */
	count = rwsem_atomic_update(adjustment, sem);

	/* If there are no active locks, wake the front queued process(es).
	 *
	 * If there are no writers and we are first in the queue,
	 * wake our own waiter to join the existing active readers !
	 */
	if (count == RWSEM_WAITING_BIAS ||
	    (count > RWSEM_WAITING_BIAS &&
	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);

	raw_spin_unlock_irq(&sem->wait_lock);

	/* wait to be given the lock */
	while (true) {
		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
		if (!waiter.task)
			break;
		schedule();
	}

	__set_task_state(tsk, TASK_RUNNING);
	return sem;
}
EXPORT_SYMBOL(rwsem_down_read_failed);

static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
{
	/*
	 * Try acquiring the write lock. Check count first in order
	 * to reduce unnecessary expensive cmpxchg() operations.
	 */
	if (count == RWSEM_WAITING_BIAS &&
	    cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS,
		    RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
		if (!list_is_singular(&sem->wait_list))
			rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
		rwsem_set_owner(sem);
		return true;
	}

	return false;
}

#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
/*
 * Try to acquire write lock before the writer has been put on wait queue.
 */
static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
{
	long old, count = READ_ONCE(sem->count);

	while (true) {
		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
			return false;

		old = cmpxchg_acquire(&sem->count, count,
				      count + RWSEM_ACTIVE_WRITE_BIAS);
		if (old == count) {
			rwsem_set_owner(sem);
			return true;
		}

		count = old;
	}
}

static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
{
	struct task_struct *owner;
	bool ret = true;

	if (need_resched())
		return false;

	rcu_read_lock();
	owner = READ_ONCE(sem->owner);
	if (!owner) {
		long count = READ_ONCE(sem->count);
		/*
		 * If sem->owner is not set, yet we have just recently entered the
		 * slowpath with the lock being active, then there is a possibility
		 * reader(s) may have the lock. To be safe, bail spinning in these
		 * situations.
		 */
		if (count & RWSEM_ACTIVE_MASK)
			ret = false;
		goto done;
	}

	ret = owner->on_cpu;
done:
	rcu_read_unlock();
	return ret;
}

static noinline
bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
{
	long count;

	rcu_read_lock();
	while (sem->owner == owner) {
		/*
		 * Ensure we emit the owner->on_cpu, dereference _after_
		 * checking sem->owner still matches owner, if that fails,
		 * owner might point to free()d memory, if it still matches,
		 * the rcu_read_lock() ensures the memory stays valid.
		 */
		barrier();

		/* abort spinning when need_resched or owner is not running */
		if (!owner->on_cpu || need_resched()) {
			rcu_read_unlock();
			return false;
		}

		cpu_relax_lowlatency();
	}
	rcu_read_unlock();

	if (READ_ONCE(sem->owner))
		return true; /* new owner, continue spinning */

	/*
	 * When the owner is not set, the lock could be free or
	 * held by readers. Check the counter to verify the
	 * state.
	 */
	count = READ_ONCE(sem->count);
	return (count == 0 || count == RWSEM_WAITING_BIAS);
}

static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
	struct task_struct *owner;
	bool taken = false;

	preempt_disable();

	/* sem->wait_lock should not be held when doing optimistic spinning */
	if (!rwsem_can_spin_on_owner(sem))
		goto done;

	if (!osq_lock(&sem->osq))
		goto done;

	while (true) {
		owner = READ_ONCE(sem->owner);
		if (owner && !rwsem_spin_on_owner(sem, owner))
			break;

		/* wait_lock will be acquired if write_lock is obtained */
		if (rwsem_try_write_lock_unqueued(sem)) {
			taken = true;
			break;
		}

		/*
		 * When there's no owner, we might have preempted between the
		 * owner acquiring the lock and setting the owner field. If
		 * we're an RT task that will live-lock because we won't let
		 * the owner complete.
		 */
		if (!owner && (need_resched() || rt_task(current)))
			break;

		/*
		 * The cpu_relax() call is a compiler barrier which forces
		 * everything in this loop to be re-loaded. We don't need
		 * memory barriers as we'll eventually observe the right
		 * values at the cost of a few extra spins.
		 */
		cpu_relax_lowlatency();
	}
	osq_unlock(&sem->osq);
done:
	preempt_enable();
	return taken;
}

/*
 * Return true if the rwsem has active spinner
 */
static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
{
	return osq_is_locked(&sem->osq);
}

#else
static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
	return false;
}

static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
{
	return false;
}
#endif

/*
 * Wait until we successfully acquire the write lock
 */
__visible
struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
{
	long count;
	bool waiting = true; /* any queued threads before us */
	struct rwsem_waiter waiter;

	/* undo write bias from down_write operation, stop active locking */
	count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);

	/* do optimistic spinning and steal lock if possible */
	if (rwsem_optimistic_spin(sem))
		return sem;

	/*
	 * Optimistic spinning failed, proceed to the slowpath
	 * and block until we can acquire the sem.
	 */
	waiter.task = current;
	waiter.type = RWSEM_WAITING_FOR_WRITE;

	raw_spin_lock_irq(&sem->wait_lock);

	/* account for this before adding a new element to the list */
	if (list_empty(&sem->wait_list))
		waiting = false;

	list_add_tail(&waiter.list, &sem->wait_list);

	/* we're now waiting on the lock, but no longer actively locking */
	if (waiting) {
		count = READ_ONCE(sem->count);

		/*
		 * If there were already threads queued before us and there are
		 * no active writers, the lock must be read owned; so we try to
		 * wake any read locks that were queued ahead of us.
		 */
		if (count > RWSEM_WAITING_BIAS)
			sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);

	} else
		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);

	/* wait until we successfully acquire the lock */
	set_current_state(TASK_UNINTERRUPTIBLE);
	while (true) {
		if (rwsem_try_write_lock(count, sem))
			break;
		raw_spin_unlock_irq(&sem->wait_lock);

		/* Block until there are no active lockers. */
		do {
			schedule();
			set_current_state(TASK_UNINTERRUPTIBLE);
		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);

		raw_spin_lock_irq(&sem->wait_lock);
	}
	__set_current_state(TASK_RUNNING);

	list_del(&waiter.list);
	raw_spin_unlock_irq(&sem->wait_lock);

	return sem;
}
EXPORT_SYMBOL(rwsem_down_write_failed);

/*
 * handle waking up a waiter on the semaphore
 * - up_read/up_write has decremented the active part of count if we come here
 */
__visible
struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
	unsigned long flags;

	/*
	 * If a spinner is present, it is not necessary to do the wakeup.
	 * Try to do wakeup only if the trylock succeeds to minimize
	 * spinlock contention which may introduce too much delay in the
	 * unlock operation.
	 *
	 *    spinning writer		up_write/up_read caller
	 *    ---------------		-----------------------
	 * [S]   osq_unlock()		[L]   osq
	 *	 MB			      RMB
	 * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
	 *
	 * Here, it is important to make sure that there won't be a missed
	 * wakeup while the rwsem is free and the only spinning writer goes
	 * to sleep without taking the rwsem. Even when the spinning writer
	 * is just going to break out of the waiting loop, it will still do
	 * a trylock in rwsem_down_write_failed() before sleeping. IOW, if
	 * rwsem_has_spinner() is true, it will guarantee at least one
	 * trylock attempt on the rwsem later on.
	 */
	if (rwsem_has_spinner(sem)) {
		/*
		 * The smp_rmb() here is to make sure that the spinner
		 * state is consulted before reading the wait_lock.
		 */
		smp_rmb();
		if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
			return sem;
		goto locked;
	}
	raw_spin_lock_irqsave(&sem->wait_lock, flags);
locked:

	/* do nothing if list empty */
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return sem;
}
EXPORT_SYMBOL(rwsem_wake);

/*
 * downgrade a write lock into a read lock
 * - caller incremented waiting part of count and discovered it still negative
 * - just wake up any readers at the front of the queue
 */
__visible
struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	/* do nothing if list empty */
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return sem;
}
EXPORT_SYMBOL(rwsem_downgrade_wake);