summaryrefslogtreecommitdiff
path: root/arch/i386/kernel/semaphore.c
blob: 469f496e55c0f56787929fa1c387572097c9ddc8 (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
/*
 * i386 semaphore implementation.
 *
 * (C) Copyright 1999 Linus Torvalds
 *
 * Portions Copyright 1999 Red Hat, Inc.
 *
 *	This program is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU General Public License
 *	as published by the Free Software Foundation; either version
 *	2 of the License, or (at your option) any later version.
 *
 * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
 */
#include <linux/config.h>
#include <linux/sched.h>
#include <linux/err.h>
#include <linux/init.h>
#include <asm/semaphore.h>

/*
 * Semaphores are implemented using a two-way counter:
 * The "count" variable is decremented for each process
 * that tries to acquire the semaphore, while the "sleeping"
 * variable is a count of such acquires.
 *
 * Notably, the inline "up()" and "down()" functions can
 * efficiently test if they need to do any extra work (up
 * needs to do something only if count was negative before
 * the increment operation.
 *
 * "sleeping" and the contention routine ordering is protected
 * by the spinlock in the semaphore's waitqueue head.
 *
 * Note that these functions are only called when there is
 * contention on the lock, and as such all this is the
 * "non-critical" part of the whole semaphore business. The
 * critical part is the inline stuff in <asm/semaphore.h>
 * where we want to avoid any extra jumps and calls.
 */

/*
 * Logic:
 *  - only on a boundary condition do we need to care. When we go
 *    from a negative count to a non-negative, we wake people up.
 *  - when we go from a non-negative count to a negative do we
 *    (a) synchronize with the "sleeper" count and (b) make sure
 *    that we're on the wakeup list before we synchronize so that
 *    we cannot lose wakeup events.
 */

static fastcall void __attribute_used__  __up(struct semaphore *sem)
{
	wake_up(&sem->wait);
}

static fastcall void __attribute_used__ __sched __down(struct semaphore * sem)
{
	struct task_struct *tsk = current;
	DECLARE_WAITQUEUE(wait, tsk);
	unsigned long flags;

	tsk->state = TASK_UNINTERRUPTIBLE;
	spin_lock_irqsave(&sem->wait.lock, flags);
	add_wait_queue_exclusive_locked(&sem->wait, &wait);

	sem->sleepers++;
	for (;;) {
		int sleepers = sem->sleepers;

		/*
		 * Add "everybody else" into it. They aren't
		 * playing, because we own the spinlock in
		 * the wait_queue_head.
		 */
		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
			sem->sleepers = 0;
			break;
		}
		sem->sleepers = 1;	/* us - see -1 above */
		spin_unlock_irqrestore(&sem->wait.lock, flags);

		schedule();

		spin_lock_irqsave(&sem->wait.lock, flags);
		tsk->state = TASK_UNINTERRUPTIBLE;
	}
	remove_wait_queue_locked(&sem->wait, &wait);
	wake_up_locked(&sem->wait);
	spin_unlock_irqrestore(&sem->wait.lock, flags);
	tsk->state = TASK_RUNNING;
}

static fastcall int __attribute_used__ __sched __down_interruptible(struct semaphore * sem)
{
	int retval = 0;
	struct task_struct *tsk = current;
	DECLARE_WAITQUEUE(wait, tsk);
	unsigned long flags;

	tsk->state = TASK_INTERRUPTIBLE;
	spin_lock_irqsave(&sem->wait.lock, flags);
	add_wait_queue_exclusive_locked(&sem->wait, &wait);

	sem->sleepers++;
	for (;;) {
		int sleepers = sem->sleepers;

		/*
		 * With signals pending, this turns into
		 * the trylock failure case - we won't be
		 * sleeping, and we* can't get the lock as
		 * it has contention. Just correct the count
		 * and exit.
		 */
		if (signal_pending(current)) {
			retval = -EINTR;
			sem->sleepers = 0;
			atomic_add(sleepers, &sem->count);
			break;
		}

		/*
		 * Add "everybody else" into it. They aren't
		 * playing, because we own the spinlock in
		 * wait_queue_head. The "-1" is because we're
		 * still hoping to get the semaphore.
		 */
		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
			sem->sleepers = 0;
			break;
		}
		sem->sleepers = 1;	/* us - see -1 above */
		spin_unlock_irqrestore(&sem->wait.lock, flags);

		schedule();

		spin_lock_irqsave(&sem->wait.lock, flags);
		tsk->state = TASK_INTERRUPTIBLE;
	}
	remove_wait_queue_locked(&sem->wait, &wait);
	wake_up_locked(&sem->wait);
	spin_unlock_irqrestore(&sem->wait.lock, flags);

	tsk->state = TASK_RUNNING;
	return retval;
}

/*
 * Trylock failed - make sure we correct for
 * having decremented the count.
 *
 * We could have done the trylock with a
 * single "cmpxchg" without failure cases,
 * but then it wouldn't work on a 386.
 */
static fastcall int __attribute_used__ __down_trylock(struct semaphore * sem)
{
	int sleepers;
	unsigned long flags;

	spin_lock_irqsave(&sem->wait.lock, flags);
	sleepers = sem->sleepers + 1;
	sem->sleepers = 0;

	/*
	 * Add "everybody else" and us into it. They aren't
	 * playing, because we own the spinlock in the
	 * wait_queue_head.
	 */
	if (!atomic_add_negative(sleepers, &sem->count)) {
		wake_up_locked(&sem->wait);
	}

	spin_unlock_irqrestore(&sem->wait.lock, flags);
	return 1;
}


/*
 * The semaphore operations have a special calling sequence that
 * allow us to do a simpler in-line version of them. These routines
 * need to convert that sequence back into the C sequence when
 * there is contention on the semaphore.
 *
 * %eax contains the semaphore pointer on entry. Save the C-clobbered
 * registers (%eax, %edx and %ecx) except %eax whish is either a return
 * value or just clobbered..
 */
asm(
".section .sched.text\n"
".align 4\n"
".globl __down_failed\n"
"__down_failed:\n\t"
#if defined(CONFIG_FRAME_POINTER)
	"pushl %ebp\n\t"
	"movl  %esp,%ebp\n\t"
#endif
	"pushl %edx\n\t"
	"pushl %ecx\n\t"
	"call __down\n\t"
	"popl %ecx\n\t"
	"popl %edx\n\t"
#if defined(CONFIG_FRAME_POINTER)
	"movl %ebp,%esp\n\t"
	"popl %ebp\n\t"
#endif
	"ret"
);

asm(
".section .sched.text\n"
".align 4\n"
".globl __down_failed_interruptible\n"
"__down_failed_interruptible:\n\t"
#if defined(CONFIG_FRAME_POINTER)
	"pushl %ebp\n\t"
	"movl  %esp,%ebp\n\t"
#endif
	"pushl %edx\n\t"
	"pushl %ecx\n\t"
	"call __down_interruptible\n\t"
	"popl %ecx\n\t"
	"popl %edx\n\t"
#if defined(CONFIG_FRAME_POINTER)
	"movl %ebp,%esp\n\t"
	"popl %ebp\n\t"
#endif
	"ret"
);

asm(
".section .sched.text\n"
".align 4\n"
".globl __down_failed_trylock\n"
"__down_failed_trylock:\n\t"
#if defined(CONFIG_FRAME_POINTER)
	"pushl %ebp\n\t"
	"movl  %esp,%ebp\n\t"
#endif
	"pushl %edx\n\t"
	"pushl %ecx\n\t"
	"call __down_trylock\n\t"
	"popl %ecx\n\t"
	"popl %edx\n\t"
#if defined(CONFIG_FRAME_POINTER)
	"movl %ebp,%esp\n\t"
	"popl %ebp\n\t"
#endif
	"ret"
);

asm(
".section .sched.text\n"
".align 4\n"
".globl __up_wakeup\n"
"__up_wakeup:\n\t"
	"pushl %edx\n\t"
	"pushl %ecx\n\t"
	"call __up\n\t"
	"popl %ecx\n\t"
	"popl %edx\n\t"
	"ret"
);

/*
 * rw spinlock fallbacks
 */
#if defined(CONFIG_SMP)
asm(
".section .sched.text\n"
".align	4\n"
".globl	__write_lock_failed\n"
"__write_lock_failed:\n\t"
	LOCK "addl	$" RW_LOCK_BIAS_STR ",(%eax)\n"
"1:	rep; nop\n\t"
	"cmpl	$" RW_LOCK_BIAS_STR ",(%eax)\n\t"
	"jne	1b\n\t"
	LOCK "subl	$" RW_LOCK_BIAS_STR ",(%eax)\n\t"
	"jnz	__write_lock_failed\n\t"
	"ret"
);

asm(
".section .sched.text\n"
".align	4\n"
".globl	__read_lock_failed\n"
"__read_lock_failed:\n\t"
	LOCK "incl	(%eax)\n"
"1:	rep; nop\n\t"
	"cmpl	$1,(%eax)\n\t"
	"js	1b\n\t"
	LOCK "decl	(%eax)\n\t"
	"js	__read_lock_failed\n\t"
	"ret"
);
#endif