aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/locking/rtmutex_api.c
blob: c5136f4998bbb7f633ebdcefbda5ec0fbd468382 (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * rtmutex API
 */
#include <linux/spinlock.h>
#include <linux/export.h>

#include "rtmutex.c"

/*
 * Max number of times we'll walk the boosting chain:
 */
int max_lock_depth = 1024;

/*
 * Debug aware fast / slowpath lock,trylock,unlock
 *
 * The atomic acquire/release ops are compiled away, when either the
 * architecture does not support cmpxchg or when debugging is enabled.
 */
static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock,
						  unsigned int state,
						  unsigned int subclass)
{
	int ret;

	might_sleep();
	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
	ret = __rt_mutex_lock(&lock->rtmutex, state);
	if (ret)
		mutex_release(&lock->dep_map, _RET_IP_);
	return ret;
}

void rt_mutex_base_init(struct rt_mutex_base *rtb)
{
	__rt_mutex_base_init(rtb);
}
EXPORT_SYMBOL(rt_mutex_base_init);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
 * rt_mutex_lock_nested - lock a rt_mutex
 *
 * @lock: the rt_mutex to be locked
 * @subclass: the lockdep subclass
 */
void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
{
	__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);

#else /* !CONFIG_DEBUG_LOCK_ALLOC */

/**
 * rt_mutex_lock - lock a rt_mutex
 *
 * @lock: the rt_mutex to be locked
 */
void __sched rt_mutex_lock(struct rt_mutex *lock)
{
	__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
#endif

/**
 * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
 *
 * @lock:		the rt_mutex to be locked
 *
 * Returns:
 *  0		on success
 * -EINTR	when interrupted by a signal
 */
int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
{
	return __rt_mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);

/**
 * rt_mutex_trylock - try to lock a rt_mutex
 *
 * @lock:	the rt_mutex to be locked
 *
 * This function can only be called in thread context. It's safe to call it
 * from atomic regions, but not from hard or soft interrupt context.
 *
 * Returns:
 *  1 on success
 *  0 on contention
 */
int __sched rt_mutex_trylock(struct rt_mutex *lock)
{
	int ret;

	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
		return 0;

	ret = __rt_mutex_trylock(&lock->rtmutex);
	if (ret)
		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);

	return ret;
}
EXPORT_SYMBOL_GPL(rt_mutex_trylock);

/**
 * rt_mutex_unlock - unlock a rt_mutex
 *
 * @lock: the rt_mutex to be unlocked
 */
void __sched rt_mutex_unlock(struct rt_mutex *lock)
{
	mutex_release(&lock->dep_map, _RET_IP_);
	__rt_mutex_unlock(&lock->rtmutex);
}
EXPORT_SYMBOL_GPL(rt_mutex_unlock);

/*
 * Futex variants, must not use fastpath.
 */
int __sched rt_mutex_futex_trylock(struct rt_mutex_base *lock)
{
	return rt_mutex_slowtrylock(lock);
}

int __sched __rt_mutex_futex_trylock(struct rt_mutex_base *lock)
{
	return __rt_mutex_slowtrylock(lock);
}

/**
 * __rt_mutex_futex_unlock - Futex variant, that since futex variants
 * do not use the fast-path, can be simple and will not need to retry.
 *
 * @lock:	The rt_mutex to be unlocked
 * @wake_q:	The wake queue head from which to get the next lock waiter
 */
bool __sched __rt_mutex_futex_unlock(struct rt_mutex_base *lock,
				     struct wake_q_head *wake_q)
{
	lockdep_assert_held(&lock->wait_lock);

	debug_rt_mutex_unlock(lock);

	if (!rt_mutex_has_waiters(lock)) {
		lock->owner = NULL;
		return false; /* done */
	}

	/*
	 * We've already deboosted, mark_wakeup_next_waiter() will
	 * retain preempt_disabled when we drop the wait_lock, to
	 * avoid inversion prior to the wakeup.  preempt_disable()
	 * therein pairs with rt_mutex_postunlock().
	 */
	mark_wakeup_next_waiter(wake_q, lock);

	return true; /* call postunlock() */
}

void __sched rt_mutex_futex_unlock(struct rt_mutex_base *lock)
{
	DEFINE_WAKE_Q(wake_q);
	unsigned long flags;
	bool postunlock;

	raw_spin_lock_irqsave(&lock->wait_lock, flags);
	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

	if (postunlock)
		rt_mutex_postunlock(&wake_q);
}

/**
 * __rt_mutex_init - initialize the rt_mutex
 *
 * @lock:	The rt_mutex to be initialized
 * @name:	The lock name used for debugging
 * @key:	The lock class key used for debugging
 *
 * Initialize the rt_mutex to unlocked state.
 *
 * Initializing of a locked rt_mutex is not allowed
 */
void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name,
			     struct lock_class_key *key)
{
	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
	__rt_mutex_base_init(&lock->rtmutex);
	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
}
EXPORT_SYMBOL_GPL(__rt_mutex_init);

/**
 * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
 *				proxy owner
 *
 * @lock:	the rt_mutex to be locked
 * @proxy_owner:the task to set as owner
 *
 * No locking. Caller has to do serializing itself
 *
 * Special API call for PI-futex support. This initializes the rtmutex and
 * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
 * possible at this point because the pi_state which contains the rtmutex
 * is not yet visible to other tasks.
 */
void __sched rt_mutex_init_proxy_locked(struct rt_mutex_base *lock,
					struct task_struct *proxy_owner)
{
	__rt_mutex_base_init(lock);
	rt_mutex_set_owner(lock, proxy_owner);
}

/**
 * rt_mutex_proxy_unlock - release a lock on behalf of owner
 *
 * @lock:	the rt_mutex to be locked
 *
 * No locking. Caller has to do serializing itself
 *
 * Special API call for PI-futex support. This just cleans up the rtmutex
 * (debugging) state. Concurrent operations on this rt_mutex are not
 * possible because it belongs to the pi_state which is about to be freed
 * and it is not longer visible to other tasks.
 */
void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
{
	debug_rt_mutex_proxy_unlock(lock);
	rt_mutex_set_owner(lock, NULL);
}

/**
 * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
 * @lock:		the rt_mutex to take
 * @waiter:		the pre-initialized rt_mutex_waiter
 * @task:		the task to prepare
 *
 * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
 * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
 *
 * NOTE: does _NOT_ remove the @waiter on failure; must either call
 * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
 *
 * Returns:
 *  0 - task blocked on lock
 *  1 - acquired the lock for task, caller should wake it up
 * <0 - error
 *
 * Special API call for PI-futex support.
 */
int __sched __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
					struct rt_mutex_waiter *waiter,
					struct task_struct *task)
{
	int ret;

	lockdep_assert_held(&lock->wait_lock);

	if (try_to_take_rt_mutex(lock, task, NULL))
		return 1;

	/* We enforce deadlock detection for futexes */
	ret = task_blocks_on_rt_mutex(lock, waiter, task,
				      RT_MUTEX_FULL_CHAINWALK);

	if (ret && !rt_mutex_owner(lock)) {
		/*
		 * Reset the return value. We might have
		 * returned with -EDEADLK and the owner
		 * released the lock while we were walking the
		 * pi chain.  Let the waiter sort it out.
		 */
		ret = 0;
	}

	return ret;
}

/**
 * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
 * @lock:		the rt_mutex to take
 * @waiter:		the pre-initialized rt_mutex_waiter
 * @task:		the task to prepare
 *
 * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
 * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
 *
 * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
 * on failure.
 *
 * Returns:
 *  0 - task blocked on lock
 *  1 - acquired the lock for task, caller should wake it up
 * <0 - error
 *
 * Special API call for PI-futex support.
 */
int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
				      struct rt_mutex_waiter *waiter,
				      struct task_struct *task)
{
	int ret;

	raw_spin_lock_irq(&lock->wait_lock);
	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
	if (unlikely(ret))
		remove_waiter(lock, waiter);
	raw_spin_unlock_irq(&lock->wait_lock);

	return ret;
}

/**
 * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
 * @lock:		the rt_mutex we were woken on
 * @to:			the timeout, null if none. hrtimer should already have
 *			been started.
 * @waiter:		the pre-initialized rt_mutex_waiter
 *
 * Wait for the lock acquisition started on our behalf by
 * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
 * rt_mutex_cleanup_proxy_lock().
 *
 * Returns:
 *  0 - success
 * <0 - error, one of -EINTR, -ETIMEDOUT
 *
 * Special API call for PI-futex support
 */
int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
				     struct hrtimer_sleeper *to,
				     struct rt_mutex_waiter *waiter)
{
	int ret;

	raw_spin_lock_irq(&lock->wait_lock);
	/* sleep on the mutex */
	set_current_state(TASK_INTERRUPTIBLE);
	ret = rt_mutex_slowlock_block(lock, TASK_INTERRUPTIBLE, to, waiter);
	/*
	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
	 * have to fix that up.
	 */
	fixup_rt_mutex_waiters(lock);
	raw_spin_unlock_irq(&lock->wait_lock);

	return ret;
}

/**
 * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
 * @lock:		the rt_mutex we were woken on
 * @waiter:		the pre-initialized rt_mutex_waiter
 *
 * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
 * rt_mutex_wait_proxy_lock().
 *
 * Unless we acquired the lock; we're still enqueued on the wait-list and can
 * in fact still be granted ownership until we're removed. Therefore we can
 * find we are in fact the owner and must disregard the
 * rt_mutex_wait_proxy_lock() failure.
 *
 * Returns:
 *  true  - did the cleanup, we done.
 *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
 *          caller should disregards its return value.
 *
 * Special API call for PI-futex support
 */
bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock,
					 struct rt_mutex_waiter *waiter)
{
	bool cleanup = false;

	raw_spin_lock_irq(&lock->wait_lock);
	/*
	 * Do an unconditional try-lock, this deals with the lock stealing
	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
	 * sets a NULL owner.
	 *
	 * We're not interested in the return value, because the subsequent
	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
	 * we will own the lock and it will have removed the waiter. If we
	 * failed the trylock, we're still not owner and we need to remove
	 * ourselves.
	 */
	try_to_take_rt_mutex(lock, current, waiter);
	/*
	 * Unless we're the owner; we're still enqueued on the wait_list.
	 * So check if we became owner, if not, take us off the wait_list.
	 */
	if (rt_mutex_owner(lock) != current) {
		remove_waiter(lock, waiter);
		cleanup = true;
	}
	/*
	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
	 * have to fix that up.
	 */
	fixup_rt_mutex_waiters(lock);

	raw_spin_unlock_irq(&lock->wait_lock);

	return cleanup;
}

/*
 * Recheck the pi chain, in case we got a priority setting
 *
 * Called from sched_setscheduler
 */
void __sched rt_mutex_adjust_pi(struct task_struct *task)
{
	struct rt_mutex_waiter *waiter;
	struct rt_mutex_base *next_lock;
	unsigned long flags;

	raw_spin_lock_irqsave(&task->pi_lock, flags);

	waiter = task->pi_blocked_on;
	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
		return;
	}
	next_lock = waiter->lock;
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);

	/* gets dropped in rt_mutex_adjust_prio_chain()! */
	get_task_struct(task);

	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
				   next_lock, NULL, task);
}

/*
 * Performs the wakeup of the top-waiter and re-enables preemption.
 */
void __sched rt_mutex_postunlock(struct wake_q_head *wake_q)
{
	wake_up_q(wake_q);

	/* Pairs with preempt_disable() in mark_wakeup_next_waiter() */
	preempt_enable();
}

#ifdef CONFIG_DEBUG_RT_MUTEXES
void rt_mutex_debug_task_free(struct task_struct *task)
{
	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters.rb_root));
	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
}
#endif