summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_shutdown.c
blob: abcf113309fe7952b4271ef1fd87af3f6da7d8fc (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
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
/*-
 * Copyright (c) 1986, 1988, 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. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. 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_shutdown.c	8.3 (Berkeley) 1/21/94
 * $FreeBSD$
 */

#include "opt_ddb.h"
#include "opt_ddb_trace.h"
#include "opt_ddb_unattended.h"
#include "opt_hw_wdog.h"
#include "opt_mac.h"
#include "opt_panic.h"
#include "opt_show_busybufs.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/conf.h>
#include <sys/cons.h>
#include <sys/eventhandler.h>
#include <sys/kernel.h>
#include <sys/kthread.h>
#include <sys/mac.h>
#include <sys/malloc.h>
#include <sys/mount.h>
#include <sys/proc.h>
#include <sys/reboot.h>
#include <sys/resourcevar.h>
#include <sys/smp.h>		/* smp_active */
#include <sys/sysctl.h>
#include <sys/sysproto.h>
#include <sys/vnode.h>

#include <machine/pcb.h>
#include <machine/md_var.h>
#include <machine/smp.h>

#include <sys/signalvar.h>
#ifdef DDB
#include <ddb/ddb.h>
#endif

#ifndef PANIC_REBOOT_WAIT_TIME
#define PANIC_REBOOT_WAIT_TIME 15 /* default to 15 seconds */
#endif

/*
 * Note that stdarg.h and the ANSI style va_start macro is used for both
 * ANSI and traditional C compilers.
 */
#include <machine/stdarg.h>

#ifdef DDB
#ifdef DDB_UNATTENDED
int debugger_on_panic = 0;
#else
int debugger_on_panic = 1;
#endif
SYSCTL_INT(_debug, OID_AUTO, debugger_on_panic, CTLFLAG_RW,
	&debugger_on_panic, 0, "Run debugger on kernel panic");

#ifdef DDB_TRACE
int trace_on_panic = 1;
#else
int trace_on_panic = 0;
#endif
SYSCTL_INT(_debug, OID_AUTO, trace_on_panic, CTLFLAG_RW,
	&trace_on_panic, 0, "Print stack trace on kernel panic");
#endif

int sync_on_panic = 1;
SYSCTL_INT(_kern, OID_AUTO, sync_on_panic, CTLFLAG_RW,
	&sync_on_panic, 0, "Do a sync before rebooting from a panic");

SYSCTL_NODE(_kern, OID_AUTO, shutdown, CTLFLAG_RW, 0, "Shutdown environment");

#ifdef	HW_WDOG
/*
 * If there is a hardware watchdog, point this at the function needed to
 * hold it off.
 * It's needed when the kernel needs to do some lengthy operations.
 * e.g. in wd.c when dumping core.. It's most annoying to have
 * your precious core-dump only half written because the wdog kicked in.
 */
watchdog_tickle_fn wdog_tickler = NULL;
#endif	/* HW_WDOG */

/*
 * Variable panicstr contains argument to first call to panic; used as flag
 * to indicate that the kernel has already called panic.
 */
const char *panicstr;

int dumping;				/* system is dumping */
static struct dumperinfo dumper;	/* our selected dumper */
static struct pcb dumppcb;		/* "You Are Here" sign for dump-debuggers */

static void boot(int) __dead2;
static void poweroff_wait(void *, int);
static void shutdown_halt(void *junk, int howto);
static void shutdown_panic(void *junk, int howto);
static void shutdown_reset(void *junk, int howto);

/* register various local shutdown events */
static void
shutdown_conf(void *unused)
{

	EVENTHANDLER_REGISTER(shutdown_final, poweroff_wait, NULL,
	    SHUTDOWN_PRI_FIRST);
	EVENTHANDLER_REGISTER(shutdown_final, shutdown_halt, NULL,
	    SHUTDOWN_PRI_LAST + 100);
	EVENTHANDLER_REGISTER(shutdown_final, shutdown_panic, NULL,
	    SHUTDOWN_PRI_LAST + 100);
	EVENTHANDLER_REGISTER(shutdown_final, shutdown_reset, NULL,
	    SHUTDOWN_PRI_LAST + 200);
}

SYSINIT(shutdown_conf, SI_SUB_INTRINSIC, SI_ORDER_ANY, shutdown_conf, NULL)

/*
 * The system call that results in a reboot
 *
 * MPSAFE
 */
/* ARGSUSED */
int
reboot(struct thread *td, struct reboot_args *uap)
{
	int error;

	error = 0;
#ifdef MAC
	error = mac_check_system_reboot(td->td_ucred, uap->opt);
#endif
	if (error == 0)
		error = suser(td);
	if (error == 0) {
		mtx_lock(&Giant);
		boot(uap->opt);
		mtx_unlock(&Giant);
	}
	return (error);
}

/*
 * Called by events that want to shut down.. e.g  <CTL><ALT><DEL> on a PC
 */
static int shutdown_howto = 0;

void
shutdown_nice(int howto)
{

	shutdown_howto = howto;

	/* Send a signal to init(8) and have it shutdown the world */
	if (initproc != NULL) {
		PROC_LOCK(initproc);
		psignal(initproc, SIGINT);
		PROC_UNLOCK(initproc);
	} else {
		/* No init(8) running, so simply reboot */
		boot(RB_NOSYNC);
	}
	return;
}
static int	waittime = -1;

static void
print_uptime(void)
{
	int f;
	struct timespec ts;

	getnanouptime(&ts);
	printf("Uptime: ");
	f = 0;
	if (ts.tv_sec >= 86400) {
		printf("%ldd", (long)ts.tv_sec / 86400);
		ts.tv_sec %= 86400;
		f = 1;
	}
	if (f || ts.tv_sec >= 3600) {
		printf("%ldh", (long)ts.tv_sec / 3600);
		ts.tv_sec %= 3600;
		f = 1;
	}
	if (f || ts.tv_sec >= 60) {
		printf("%ldm", (long)ts.tv_sec / 60);
		ts.tv_sec %= 60;
		f = 1;
	}
	printf("%lds\n", (long)ts.tv_sec);
}

static void
doadump(void)
{

	savectx(&dumppcb);
	dumping++;
	dumpsys(&dumper);
}

/*
 *  Go through the rigmarole of shutting down..
 * this used to be in machdep.c but I'll be dammned if I could see
 * anything machine dependant in it.
 */
static void
boot(int howto)
{

	/* collect extra flags that shutdown_nice might have set */
	howto |= shutdown_howto;

#ifdef DDB
	/* We are out of the debugger now. */
	db_active = 0;
#endif

#ifdef SMP
	if (smp_active)
		printf("boot() called on cpu#%d\n", PCPU_GET(cpuid));
#endif
	/*
	 * Do any callouts that should be done BEFORE syncing the filesystems.
	 */
	EVENTHANDLER_INVOKE(shutdown_pre_sync, howto);

	/* 
	 * Now sync filesystems
	 */
	if (!cold && (howto & RB_NOSYNC) == 0 && waittime < 0) {
		register struct buf *bp;
		int iter, nbusy, pbusy;
		int subiter;

		waittime = 0;
		printf("\nsyncing disks, buffers remaining... ");

		sync(&thread0, NULL);

		/*
		 * With soft updates, some buffers that are
		 * written will be remarked as dirty until other
		 * buffers are written.
		 */
		for (iter = pbusy = 0; iter < 20; iter++) {
			nbusy = 0;
			for (bp = &buf[nbuf]; --bp >= buf; ) {
				if ((bp->b_flags & B_INVAL) == 0 &&
				    BUF_REFCNT(bp) > 0) {
					nbusy++;
				} else if ((bp->b_flags & (B_DELWRI | B_INVAL))
						== B_DELWRI) {
					/* bawrite(bp);*/
					nbusy++;
				}
			}
			if (nbusy == 0)
				break;
			printf("%d ", nbusy);
			if (nbusy < pbusy)
				iter = 0;
			pbusy = nbusy;
			sync(&thread0, NULL);
 			if (curthread != NULL) {
				DROP_GIANT();
   				for (subiter = 0; subiter < 50 * iter; subiter++) {
     					mtx_lock_spin(&sched_lock);
					curthread->td_proc->p_stats->p_ru.ru_nvcsw++;
     					mi_switch(); /* Allow interrupt threads to run */
     					mtx_unlock_spin(&sched_lock);
     					DELAY(1000);
   				}
				PICKUP_GIANT();
 			} else
			DELAY(50000 * iter);
		}
		printf("\n");
		/*
		 * Count only busy local buffers to prevent forcing 
		 * a fsck if we're just a client of a wedged NFS server
		 */
		nbusy = 0;
		for (bp = &buf[nbuf]; --bp >= buf; ) {
			if (((bp->b_flags&B_INVAL) == 0 && BUF_REFCNT(bp)) ||
			    ((bp->b_flags & (B_DELWRI|B_INVAL)) == B_DELWRI)) {
				if (bp->b_dev == NODEV) {
					TAILQ_REMOVE(&mountlist,
					    bp->b_vp->v_mount, mnt_list);
					continue;
				}
				nbusy++;
#if defined(SHOW_BUSYBUFS) || defined(DIAGNOSTIC)
				printf(
			    "%d: dev:%s, flags:%0x, blkno:%ld, lblkno:%ld\n",
				    nbusy, devtoname(bp->b_dev),
				    bp->b_flags, (long)bp->b_blkno,
				    (long)bp->b_lblkno);
#endif
			}
		}
		if (nbusy) {
			/*
			 * Failed to sync all blocks. Indicate this and don't
			 * unmount filesystems (thus forcing an fsck on reboot).
			 */
			printf("giving up on %d buffers\n", nbusy);
			DELAY(5000000);	/* 5 seconds */
		} else {
			printf("done\n");
			/*
			 * Unmount filesystems
			 */
			if (panicstr == 0)
				vfs_unmountall();
		}
		DELAY(100000);		/* wait for console output to finish */
	}

	print_uptime();

	/*
	 * Ok, now do things that assume all filesystem activity has
	 * been completed.
	 */
	EVENTHANDLER_INVOKE(shutdown_post_sync, howto);
	splhigh();
	if ((howto & (RB_HALT|RB_DUMP)) == RB_DUMP &&
	    !cold && dumper.dumper != NULL && !dumping) 
		doadump();

	/* Now that we're going to really halt the system... */
	EVENTHANDLER_INVOKE(shutdown_final, howto);

	for(;;) ;	/* safety against shutdown_reset not working */
	/* NOTREACHED */
}

/*
 * If the shutdown was a clean halt, behave accordingly.
 */
static void
shutdown_halt(void *junk, int howto)
{

	if (howto & RB_HALT) {
		printf("\n");
		printf("The operating system has halted.\n");
		printf("Please press any key to reboot.\n\n");
		switch (cngetc()) {
		case -1:		/* No console, just die */
			cpu_halt();
			/* NOTREACHED */
		default:
			howto &= ~RB_HALT;
			break;
		}
	}
}

/*
 * Check to see if the system paniced, pause and then reboot
 * according to the specified delay.
 */
static void
shutdown_panic(void *junk, int howto)
{
	int loop;

	if (howto & RB_DUMP) {
		if (PANIC_REBOOT_WAIT_TIME != 0) {
			if (PANIC_REBOOT_WAIT_TIME != -1) {
				printf("Automatic reboot in %d seconds - "
				       "press a key on the console to abort\n",
					PANIC_REBOOT_WAIT_TIME);
				for (loop = PANIC_REBOOT_WAIT_TIME * 10;
				     loop > 0; --loop) {
					DELAY(1000 * 100); /* 1/10th second */
					/* Did user type a key? */
					if (cncheckc() != -1)
						break;
				}
				if (!loop)
					return;
			}
		} else { /* zero time specified - reboot NOW */
			return;
		}
		printf("--> Press a key on the console to reboot,\n");
		printf("--> or switch off the system now.\n");
		cngetc();
	}
}

/*
 * Everything done, now reset
 */
static void
shutdown_reset(void *junk, int howto)
{

	printf("Rebooting...\n");
	DELAY(1000000);	/* wait 1 sec for printf's to complete and be read */
	/* cpu_boot(howto); */ /* doesn't do anything at the moment */
	cpu_reset();
	/* NOTREACHED */ /* assuming reset worked */
}

/*
 * Print a backtrace if we can.
 */

void
backtrace(void)
{

#ifdef DDB
	printf("Stack backtrace:\n");
	db_print_backtrace();
#else
	printf("Sorry, need DDB option to print backtrace");
#endif
}

#ifdef SMP
static u_int panic_cpu = NOCPU;
#endif

/*
 * Panic is called on unresolvable fatal errors.  It prints "panic: mesg",
 * and then reboots.  If we are called twice, then we avoid trying to sync
 * the disks as this often leads to recursive panics.
 *
 * MPSAFE
 */
void
panic(const char *fmt, ...)
{
	struct thread *td = curthread;
	int bootopt, newpanic;
	va_list ap;
	static char buf[256];

#ifdef SMP
	/*
	 * We don't want multiple CPU's to panic at the same time, so we
	 * use panic_cpu as a simple spinlock.  We have to keep checking
	 * panic_cpu if we are spinning in case the panic on the first
	 * CPU is canceled.
	 */
	if (panic_cpu != PCPU_GET(cpuid))
		while (atomic_cmpset_int(&panic_cpu, NOCPU,
		    PCPU_GET(cpuid)) == 0)
			while (panic_cpu != NOCPU)
				; /* nothing */
#endif

	bootopt = RB_AUTOBOOT | RB_DUMP;
	newpanic = 0;
	if (panicstr)
		bootopt |= RB_NOSYNC;
	else {
		panicstr = fmt;
		newpanic = 1;
	}

	va_start(ap, fmt);
	(void)vsnprintf(buf, sizeof(buf), fmt, ap);
	if (panicstr == fmt)
		panicstr = buf;
	va_end(ap);
	printf("panic: %s\n", buf);
#ifdef SMP
	/* two separate prints in case of an unmapped page and trap */
	printf("cpuid = %d; ", PCPU_GET(cpuid));
#ifdef APIC_IO
	printf("lapic.id = %08x\n", lapic.id);
#else
	printf("\n");
#endif
#endif

#if defined(DDB)
	if (newpanic && trace_on_panic)
		backtrace();
	if (debugger_on_panic)
		Debugger ("panic");
#ifdef RESTARTABLE_PANICS
	/* See if the user aborted the panic, in which case we continue. */
	if (panicstr == NULL) {
#ifdef SMP
		atomic_store_rel_int(&panic_cpu, NOCPU);
#endif
		return;
	}
#endif
#endif
	mtx_lock_spin(&sched_lock);
	td->td_flags |= TDF_INPANIC;
	mtx_unlock_spin(&sched_lock);
	if (!sync_on_panic)
		bootopt |= RB_NOSYNC;
	boot(bootopt);
}

/*
 * Support for poweroff delay.
 */
#ifndef POWEROFF_DELAY
# define POWEROFF_DELAY 5000
#endif
static int poweroff_delay = POWEROFF_DELAY;

SYSCTL_INT(_kern_shutdown, OID_AUTO, poweroff_delay, CTLFLAG_RW,
	&poweroff_delay, 0, "");

static void
poweroff_wait(void *junk, int howto)
{

	if (!(howto & RB_POWEROFF) || poweroff_delay <= 0)
		return;
	DELAY(poweroff_delay * 1000);
}

/*
 * Some system processes (e.g. syncer) need to be stopped at appropriate
 * points in their main loops prior to a system shutdown, so that they
 * won't interfere with the shutdown process (e.g. by holding a disk buf
 * to cause sync to fail).  For each of these system processes, register
 * shutdown_kproc() as a handler for one of shutdown events.
 */
static int kproc_shutdown_wait = 60;
SYSCTL_INT(_kern_shutdown, OID_AUTO, kproc_shutdown_wait, CTLFLAG_RW,
    &kproc_shutdown_wait, 0, "");

void
kproc_shutdown(void *arg, int howto)
{
	struct proc *p;
	int error;

	if (panicstr)
		return;

	p = (struct proc *)arg;
	printf("Waiting (max %d seconds) for system process `%s' to stop...",
	    kproc_shutdown_wait, p->p_comm);
	error = kthread_suspend(p, kproc_shutdown_wait * hz);

	if (error == EWOULDBLOCK)
		printf("timed out\n");
	else
		printf("stopped\n");
}

/* Registration of dumpers */
int
set_dumper(struct dumperinfo *di)
{

	if (di == NULL) {
		bzero(&dumper, sizeof dumper);
		return (0);
	}
	if (dumper.dumper != NULL)
		return (EBUSY);
	dumper = *di;
	return (0);
}

#if defined(__powerpc__)
void
dumpsys(struct dumperinfo *di __unused)
{

	printf("Kernel dumps not implemented on this architecture\n");
}
#endif
OpenPOWER on IntegriCloud