summaryrefslogtreecommitdiff
path: root/kernel/locking/rwsem-spinlock.c
blob: 5eacab880f672c40859709a0021c50e68e57f15f (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
/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
 * generic spinlock implementation
 *
 * Copyright (c) 2001   David Howells (dhowells@redhat.com).
 * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
 * - Derived also from comments by Linus
 */
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/export.h>

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;
};

int rwsem_is_locked(struct rw_semaphore *sem)
{
	int ret = 1;
	unsigned long flags;

	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
		ret = (sem->count != 0);
		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
	}
	return ret;
}
EXPORT_SYMBOL(rwsem_is_locked);

/*
 * initialise the semaphore
 */
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 = 0;
	raw_spin_lock_init(&sem->wait_lock);
	INIT_LIST_HEAD(&sem->wait_list);
}
EXPORT_SYMBOL(__init_rwsem);

/*
 * handle the lock release when processes blocked on it that can now run
 * - if we come here, then:
 *   - the 'active count' _reached_ zero
 *   - the 'waiting count' is non-zero
 * - 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 wakewrite is non-zero
 */
static inline struct rw_semaphore *
__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
{
	struct rwsem_waiter *waiter;
	struct task_struct *tsk;
	int woken;

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

	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
		if (wakewrite)
			/* Wake up a writer. Note that we do not grant it the
			 * lock - it will have to acquire it when it runs. */
			wake_up_process(waiter->task);
		goto out;
	}

	/* grant an infinite number of read locks to the front of the queue */
	woken = 0;
	do {
		struct list_head *next = waiter->list.next;

		list_del(&waiter->list);
		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);
		woken++;
		if (next == &sem->wait_list)
			break;
		waiter = list_entry(next, struct rwsem_waiter, list);
	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);

	sem->count += woken;

 out:
	return sem;
}

/*
 * wake a single writer
 */
static inline struct rw_semaphore *
__rwsem_wake_one_writer(struct rw_semaphore *sem)
{
	struct rwsem_waiter *waiter;

	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
	wake_up_process(waiter->task);

	return sem;
}

/*
 * get a read lock on the semaphore
 */
void __sched __down_read(struct rw_semaphore *sem)
{
	struct rwsem_waiter waiter;
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
		/* granted */
		sem->count++;
		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
		goto out;
	}

	set_current_state(TASK_UNINTERRUPTIBLE);

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

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

	/* we don't need to touch the semaphore struct anymore */
	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	/* wait to be given the lock */
	for (;;) {
		if (!waiter.task)
			break;
		schedule();
		set_current_state(TASK_UNINTERRUPTIBLE);
	}

	__set_current_state(TASK_RUNNING);
 out:
	;
}

/*
 * trylock for reading -- returns 1 if successful, 0 if contention
 */
int __down_read_trylock(struct rw_semaphore *sem)
{
	unsigned long flags;
	int ret = 0;


	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
		/* granted */
		sem->count++;
		ret = 1;
	}

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return ret;
}

/*
 * get a write lock on the semaphore
 */
int __sched __down_write_common(struct rw_semaphore *sem, int state)
{
	struct rwsem_waiter waiter;
	unsigned long flags;
	int ret = 0;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	/* set up my own style of waitqueue */
	waiter.task = current;
	waiter.type = RWSEM_WAITING_FOR_WRITE;
	list_add_tail(&waiter.list, &sem->wait_list);

	/* wait for someone to release the lock */
	for (;;) {
		/*
		 * That is the key to support write lock stealing: allows the
		 * task already on CPU to get the lock soon rather than put
		 * itself into sleep and waiting for system woke it or someone
		 * else in the head of the wait list up.
		 */
		if (sem->count == 0)
			break;
		if (signal_pending_state(state, current)) {
			ret = -EINTR;
			goto out;
		}
		set_current_state(state);
		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
		schedule();
		raw_spin_lock_irqsave(&sem->wait_lock, flags);
	}
	/* got the lock */
	sem->count = -1;
out:
	list_del(&waiter.list);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return ret;
}

void __sched __down_write(struct rw_semaphore *sem)
{
	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
}

int __sched __down_write_killable(struct rw_semaphore *sem)
{
	return __down_write_common(sem, TASK_KILLABLE);
}

/*
 * trylock for writing -- returns 1 if successful, 0 if contention
 */
int __down_write_trylock(struct rw_semaphore *sem)
{
	unsigned long flags;
	int ret = 0;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (sem->count == 0) {
		/* got the lock */
		sem->count = -1;
		ret = 1;
	}

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);

	return ret;
}

/*
 * release a read lock on the semaphore
 */
void __up_read(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (--sem->count == 0 && !list_empty(&sem->wait_list))
		sem = __rwsem_wake_one_writer(sem);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

/*
 * release a write lock on the semaphore
 */
void __up_write(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	sem->count = 0;
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, 1);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}

/*
 * downgrade a write lock into a read lock
 * - just wake up any readers at the front of the queue
 */
void __downgrade_write(struct rw_semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	sem->count = 1;
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, 0);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}