summaryrefslogtreecommitdiff
path: root/sys/kern/kern_synch.c
blob: 4b711711c02df1e07279ac51611401f5aa591e0b (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
/*	$OpenBSD: kern_synch.c,v 1.98 2011/12/11 19:42:28 guenther Exp $	*/
/*	$NetBSD: kern_synch.c,v 1.37 1996/04/22 01:38:37 christos Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1990, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)kern_synch.c	8.6 (Berkeley) 1/21/94
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/kernel.h>
#include <sys/buf.h>
#include <sys/signalvar.h>
#include <sys/resourcevar.h>
#include <uvm/uvm_extern.h>
#include <sys/sched.h>
#include <sys/timeout.h>
#include <sys/mount.h>
#include <sys/syscallargs.h>
#include <sys/pool.h>

#include <machine/spinlock.h>

#ifdef KTRACE
#include <sys/ktrace.h>
#endif


/*
 * We're only looking at 7 bits of the address; everything is
 * aligned to 4, lots of things are aligned to greater powers
 * of 2.  Shift right by 8, i.e. drop the bottom 256 worth.
 */
#define TABLESIZE	128
#define LOOKUP(x)	(((long)(x) >> 8) & (TABLESIZE - 1))
TAILQ_HEAD(slpque,proc) slpque[TABLESIZE];

void
sleep_queue_init(void)
{
	int i;

	for (i = 0; i < TABLESIZE; i++)
		TAILQ_INIT(&slpque[i]);
}


/*
 * During autoconfiguration or after a panic, a sleep will simply
 * lower the priority briefly to allow interrupts, then return.
 * The priority to be used (safepri) is machine-dependent, thus this
 * value is initialized and maintained in the machine-dependent layers.
 * This priority will typically be 0, or the lowest priority
 * that is safe for use on the interrupt stack; it can be made
 * higher to block network software interrupts after panics.
 */
extern int safepri;

/*
 * General sleep call.  Suspends the current process until a wakeup is
 * performed on the specified identifier.  The process will then be made
 * runnable with the specified priority.  Sleeps at most timo/hz seconds
 * (0 means no timeout).  If pri includes PCATCH flag, signals are checked
 * before and after sleeping, else signals are not checked.  Returns 0 if
 * awakened, EWOULDBLOCK if the timeout expires.  If PCATCH is set and a
 * signal needs to be delivered, ERESTART is returned if the current system
 * call should be restarted if possible, and EINTR is returned if the system
 * call should be interrupted by the signal (return EINTR).
 */
int
tsleep(const volatile void *ident, int priority, const char *wmesg, int timo)
{
	struct sleep_state sls;
	int error, error1;

	if (cold || panicstr) {
		int s;
		/*
		 * After a panic, or during autoconfiguration,
		 * just give interrupts a chance, then just return;
		 * don't run any other procs or panic below,
		 * in case this is the idle process and already asleep.
		 */
		s = splhigh();
		splx(safepri);
		splx(s);
		return (0);
	}

	sleep_setup(&sls, ident, priority, wmesg);
	sleep_setup_timeout(&sls, timo);
	sleep_setup_signal(&sls, priority);

	sleep_finish(&sls, 1);
	error1 = sleep_finish_timeout(&sls);
	error = sleep_finish_signal(&sls);

	/* Signal errors are higher priority than timeouts. */
	if (error == 0 && error1 != 0)
		error = error1;

	return (error);
}

/*
 * Same as tsleep, but if we have a mutex provided, then once we've 
 * entered the sleep queue we drop the mutex. After sleeping we re-lock.
 */
int
msleep(const volatile void *ident, struct mutex *mtx, int priority,
    const char *wmesg, int timo)
{
	struct sleep_state sls;
	int error, error1, spl;

	sleep_setup(&sls, ident, priority, wmesg);
	sleep_setup_timeout(&sls, timo);
	sleep_setup_signal(&sls, priority);

	if (mtx) {
		/* XXX - We need to make sure that the mutex doesn't
		 * unblock splsched. This can be made a bit more 
		 * correct when the sched_lock is a mutex.
		 */
		spl = MUTEX_OLDIPL(mtx);
		MUTEX_OLDIPL(mtx) = splsched();
		mtx_leave(mtx);
	}

	sleep_finish(&sls, 1);
	error1 = sleep_finish_timeout(&sls);
	error = sleep_finish_signal(&sls);

	if (mtx) {
		if ((priority & PNORELOCK) == 0) {
			mtx_enter(mtx);
			MUTEX_OLDIPL(mtx) = spl; /* put the ipl back */
		} else
			splx(spl);
	}
	/* Signal errors are higher priority than timeouts. */
	if (error == 0 && error1 != 0)
		error = error1;

	return (error);
}

void
sleep_setup(struct sleep_state *sls, const volatile void *ident, int prio,
    const char *wmesg)
{
	struct proc *p = curproc;

#ifdef DIAGNOSTIC
	if (ident == NULL)
		panic("tsleep: no ident");
	if (p->p_stat != SONPROC)
		panic("tsleep: not SONPROC");
#endif

#ifdef KTRACE
	if (KTRPOINT(p, KTR_CSW))
		ktrcsw(p, 1, 0);
#endif

	sls->sls_catch = 0;
	sls->sls_do_sleep = 1;
	sls->sls_sig = 1;

	SCHED_LOCK(sls->sls_s);

	p->p_wchan = ident;
	p->p_wmesg = wmesg;
	p->p_slptime = 0;
	p->p_priority = prio & PRIMASK;
	TAILQ_INSERT_TAIL(&slpque[LOOKUP(ident)], p, p_runq);
}

void
sleep_finish(struct sleep_state *sls, int do_sleep)
{
	struct proc *p = curproc;

	if (sls->sls_do_sleep && do_sleep) {
		p->p_stat = SSLEEP;
		p->p_stats->p_ru.ru_nvcsw++;
		SCHED_ASSERT_LOCKED();
		mi_switch();
	} else if (!do_sleep) {
		unsleep(p);
	}

#ifdef DIAGNOSTIC
	if (p->p_stat != SONPROC)
		panic("sleep_finish !SONPROC");
#endif

	p->p_cpu->ci_schedstate.spc_curpriority = p->p_usrpri;
	SCHED_UNLOCK(sls->sls_s);

	/*
	 * Even though this belongs to the signal handling part of sleep,
	 * we need to clear it before the ktrace.
	 */
	atomic_clearbits_int(&p->p_flag, P_SINTR);

#ifdef KTRACE
	if (KTRPOINT(p, KTR_CSW))
		ktrcsw(p, 0, 0);
#endif
}

void
sleep_setup_timeout(struct sleep_state *sls, int timo)
{
	if (timo)
		timeout_add(&curproc->p_sleep_to, timo);
}

int
sleep_finish_timeout(struct sleep_state *sls)
{
	struct proc *p = curproc;

	if (p->p_flag & P_TIMEOUT) {
		atomic_clearbits_int(&p->p_flag, P_TIMEOUT);
		return (EWOULDBLOCK);
	} else if (timeout_pending(&p->p_sleep_to)) {
		timeout_del(&p->p_sleep_to);
	}

	return (0);
}

void
sleep_setup_signal(struct sleep_state *sls, int prio)
{
	struct proc *p = curproc;

	if ((sls->sls_catch = (prio & PCATCH)) == 0)
		return;

	/*
	 * We put ourselves on the sleep queue and start our timeout
	 * before calling CURSIG, as we could stop there, and a wakeup
	 * or a SIGCONT (or both) could occur while we were stopped.
	 * A SIGCONT would cause us to be marked as SSLEEP
	 * without resuming us, thus we must be ready for sleep
	 * when CURSIG is called.  If the wakeup happens while we're
	 * stopped, p->p_wchan will be 0 upon return from CURSIG.
	 */
	atomic_setbits_int(&p->p_flag, P_SINTR);
	if (p->p_p->ps_single != NULL || (sls->sls_sig = CURSIG(p)) != 0) {
		if (p->p_wchan)
			unsleep(p);
		p->p_stat = SONPROC;
		sls->sls_do_sleep = 0;
	} else if (p->p_wchan == 0) {
		sls->sls_catch = 0;
		sls->sls_do_sleep = 0;
	}
}

int
sleep_finish_signal(struct sleep_state *sls)
{
	struct proc *p = curproc;
	int error;

	if (sls->sls_catch != 0) {
		if ((error = single_thread_check(p, 1)))
			return (error);
		if (sls->sls_sig != 0 || (sls->sls_sig = CURSIG(p)) != 0) {
			if (p->p_sigacts->ps_sigintr & sigmask(sls->sls_sig))
				return (EINTR);
			return (ERESTART);
		}
	}

	return (0);
}

/*
 * Implement timeout for tsleep.
 * If process hasn't been awakened (wchan non-zero),
 * set timeout flag and undo the sleep.  If proc
 * is stopped, just unsleep so it will remain stopped.
 */
void
endtsleep(void *arg)
{
	struct proc *p = arg;
	int s;

	SCHED_LOCK(s);
	if (p->p_wchan) {
		if (p->p_stat == SSLEEP)
			setrunnable(p);
		else
			unsleep(p);
		atomic_setbits_int(&p->p_flag, P_TIMEOUT);
	}
	SCHED_UNLOCK(s);
}

/*
 * Remove a process from its wait queue
 */
void
unsleep(struct proc *p)
{
	if (p->p_wchan) {
		TAILQ_REMOVE(&slpque[LOOKUP(p->p_wchan)], p, p_runq);
		p->p_wchan = NULL;
	}
}

/*
 * Make a number of processes sleeping on the specified identifier runnable.
 */
void
wakeup_n(const volatile void *ident, int n)
{
	struct slpque *qp;
	struct proc *p;
	struct proc *pnext;
	int s;

	SCHED_LOCK(s);
	qp = &slpque[LOOKUP(ident)];
	for (p = TAILQ_FIRST(qp); p != NULL && n != 0; p = pnext) {
		pnext = TAILQ_NEXT(p, p_runq);
#ifdef DIAGNOSTIC
		if (p->p_stat != SSLEEP && p->p_stat != SSTOP)
			panic("wakeup: p_stat is %d", (int)p->p_stat);
#endif
		if (p->p_wchan == ident) {
			--n;
			p->p_wchan = 0;
			TAILQ_REMOVE(qp, p, p_runq);
			if (p->p_stat == SSLEEP) {
				/* OPTIMIZED EXPANSION OF setrunnable(p); */
				if (p->p_slptime > 1)
					updatepri(p);
				p->p_slptime = 0;
				p->p_stat = SRUN;
				p->p_cpu = sched_choosecpu(p);
				setrunqueue(p);
				need_resched(p->p_cpu);
				/* END INLINE EXPANSION */

			}
		}
	}
	SCHED_UNLOCK(s);
}

/*
 * Make all processes sleeping on the specified identifier runnable.
 */
void
wakeup(const volatile void *chan)
{
	wakeup_n(chan, -1);
}

int
sys_sched_yield(struct proc *p, void *v, register_t *retval)
{
	yield();
	return (0);
}

int
sys_thrsleep(struct proc *p, void *v, register_t *revtal)
{
	struct sys_thrsleep_args /* {
		syscallarg(void *) ident;
		syscallarg(clockid_t) clock_id;
		syscallarg(struct timespec *) tp;
		syscallarg(void *) lock;
	} */ *uap = v;
	long ident = (long)SCARG(uap, ident);
	_spinlock_lock_t *lock = SCARG(uap, lock);
	static _spinlock_lock_t unlocked = _SPINLOCK_UNLOCKED;
	long long to_ticks = 0;
	int error;

	if (!rthreads_enabled)
		return (ENOTSUP);
	if (SCARG(uap, tp) != NULL) {
		struct timespec now, ats;

		if ((error = copyin(SCARG(uap, tp), &ats, sizeof(ats))) != 0 ||
		    (error = clock_gettime(p, SCARG(uap, clock_id), &now)) != 0)
			return (error);

		if (timespeccmp(&ats, &now, <)) {
			/* already passed: still do the unlock */
			if (lock) {
				if ((error = copyout(&unlocked, lock,
				    sizeof(unlocked))) != 0)
					return (error);
			}
			return (EWOULDBLOCK);
		}

		timespecsub(&ats, &now, &ats);
		to_ticks = (long long)hz * ats.tv_sec +
		    ats.tv_nsec / (tick * 1000);
		if (to_ticks > INT_MAX)
			to_ticks = INT_MAX;
		if (to_ticks == 0)
			to_ticks = 1;
	}

	p->p_thrslpid = ident;

	if (lock) {
		if ((error = copyout(&unlocked, lock, sizeof(unlocked))) != 0)
			return (error);
	}
	error = tsleep(&p->p_thrslpid, PUSER | PCATCH, "thrsleep",
	    (int)to_ticks);

	if (error == ERESTART)
		error = EINTR;

	return (error);

}

int
sys_thrwakeup(struct proc *p, void *v, register_t *retval)
{
	struct sys_thrwakeup_args /* {
		syscallarg(void *) ident;
		syscallarg(int) n;
	} */ *uap = v;
	long ident = (long)SCARG(uap, ident);
	int n = SCARG(uap, n);
	struct proc *q;
	int found = 0;

	if (!rthreads_enabled)
		return (ENOTSUP);
	TAILQ_FOREACH(q, &p->p_p->ps_threads, p_thr_link) {
		if (q->p_thrslpid == ident) {
			wakeup_one(&q->p_thrslpid);
			q->p_thrslpid = 0;
			if (++found == n)
				return (0);
		}
	}
	if (!found)
		return (ESRCH);

	return (0);
}