summaryrefslogtreecommitdiff
path: root/lib/rwsem.c
blob: 917fd946b4951147ba2971fe86c3958b33d63434 (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
/* rwsem.c: R/W semaphores: contention handling functions
 *
 * Written by David Howells (dhowells@redhat.com).
 * Derived from arch/i386/kernel/semaphore.c
 */
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/module.h>

/*
 * 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;
	spin_lock_init(&sem->wait_lock);
	INIT_LIST_HEAD(&sem->wait_list);
}

EXPORT_SYMBOL(__init_rwsem);

struct rwsem_waiter {
	struct list_head list;
	struct task_struct *task;
	unsigned int flags;
#define RWSEM_WAITING_FOR_READ	0x00000001
#define RWSEM_WAITING_FOR_WRITE	0x00000002
};

/*
 * 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 inline struct rw_semaphore *
__rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
{
	struct rwsem_waiter *waiter;
	struct task_struct *tsk;
	struct list_head *next;
	signed long oldcount, woken, loop;

	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
	if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE))
		goto readers_only;

	if (downgrading)
		goto out;

	/* There's a writer at the front of the queue - try to grant it the
	 * write lock.  However, we only wake this writer if we can transition
	 * the active part of the count from 0 -> 1
	 */
 try_again_write:
	oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem)
						- RWSEM_ACTIVE_BIAS;
	if (oldcount & RWSEM_ACTIVE_MASK)
		/* Someone grabbed the sem already */
		goto undo_write;

	/* We must be careful not to touch 'waiter' after we set ->task = NULL.
	 * It is an allocated on the waiter's stack and may become invalid at
	 * any time after that point (due to a wakeup from another source).
	 */
	list_del(&waiter->list);
	tsk = waiter->task;
	smp_mb();
	waiter->task = NULL;
	wake_up_process(tsk);
	put_task_struct(tsk);
	goto out;

 readers_only:
	if (downgrading)
		goto wake_readers;

	/* if we came through an up_xxxx() call, we only only wake someone up
	 * if we can transition the active part of the count from 0 -> 1 */
 try_again_read:
	oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem)
						- RWSEM_ACTIVE_BIAS;
	if (oldcount & RWSEM_ACTIVE_MASK)
		/* Someone grabbed the sem already */
		goto undo_read;

 wake_readers:
	/* 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->flags & RWSEM_WAITING_FOR_READ);

	loop = woken;
	woken *= RWSEM_ACTIVE_BIAS - RWSEM_WAITING_BIAS;
	if (!downgrading)
		/* we'd already done one increment earlier */
		woken -= RWSEM_ACTIVE_BIAS;

	rwsem_atomic_add(woken, sem);

	next = sem->wait_list.next;
	for (; loop > 0; loop--) {
		waiter = list_entry(next, struct rwsem_waiter, list);
		next = waiter->list.next;
		tsk = waiter->task;
		smp_mb();
		waiter->task = NULL;
		wake_up_process(tsk);
		put_task_struct(tsk);
	}

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

 out:
	return sem;

	/* undo the change to the active count, but check for a transition
	 * 1->0 */
 undo_write:
	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
		goto out;
	goto try_again_write;
 undo_read:
	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
		goto out;
	goto try_again_read;
}

/*
 * wait for a lock to be granted
 */
static struct rw_semaphore __sched *
rwsem_down_failed_common(struct rw_semaphore *sem,
			struct rwsem_waiter *waiter, signed long adjustment)
{
	struct task_struct *tsk = current;
	signed long count;

	set_task_state(tsk, TASK_UNINTERRUPTIBLE);

	/* set up my own style of waitqueue */
	spin_lock_irq(&sem->wait_lock);
	waiter->task = tsk;
	get_task_struct(tsk);

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

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

	/* if there are no active locks, wake the front queued process(es) up */
	if (!(count & RWSEM_ACTIVE_MASK))
		sem = __rwsem_do_wake(sem, 0);

	spin_unlock_irq(&sem->wait_lock);

	/* wait to be given the lock */
	for (;;) {
		if (!waiter->task)
			break;
		schedule();
		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
	}

	tsk->state = TASK_RUNNING;

	return sem;
}

/*
 * wait for the read lock to be granted
 */
asmregparm struct rw_semaphore __sched *
rwsem_down_read_failed(struct rw_semaphore *sem)
{
	struct rwsem_waiter waiter;

	waiter.flags = RWSEM_WAITING_FOR_READ;
	rwsem_down_failed_common(sem, &waiter,
				RWSEM_WAITING_BIAS - RWSEM_ACTIVE_BIAS);
	return sem;
}

/*
 * wait for the write lock to be granted
 */
asmregparm struct rw_semaphore __sched *
rwsem_down_write_failed(struct rw_semaphore *sem)
{
	struct rwsem_waiter waiter;

	waiter.flags = RWSEM_WAITING_FOR_WRITE;
	rwsem_down_failed_common(sem, &waiter, -RWSEM_ACTIVE_BIAS);

	return sem;
}

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

	spin_lock_irqsave(&sem->wait_lock, flags);

	/* do nothing if list empty */
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, 0);

	spin_unlock_irqrestore(&sem->wait_lock, flags);

	return sem;
}

/*
 * 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
 */
asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
	unsigned long flags;

	spin_lock_irqsave(&sem->wait_lock, flags);

	/* do nothing if list empty */
	if (!list_empty(&sem->wait_list))
		sem = __rwsem_do_wake(sem, 1);

	spin_unlock_irqrestore(&sem->wait_lock, flags);

	return sem;
}

EXPORT_SYMBOL(rwsem_down_read_failed);
EXPORT_SYMBOL(rwsem_down_write_failed);
EXPORT_SYMBOL(rwsem_wake);
EXPORT_SYMBOL(rwsem_downgrade_wake);