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
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
|
/*
* Copyright (c) 1995 Terrence R. Lambert
* All rights reserved.
*
* Copyright (c) 1982, 1986, 1989, 1991, 1992, 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.
*
* @(#)init_main.c 8.9 (Berkeley) 1/21/94
* $Id: init_main.c,v 1.98 1998/10/09 23:42:47 peter Exp $
*/
#include "opt_devfs.h"
#include <sys/param.h>
#include <sys/file.h>
#include <sys/filedesc.h>
#include <sys/kernel.h>
#include <sys/mount.h>
#include <sys/sysctl.h>
#include <sys/proc.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/systm.h>
#include <sys/vnode.h>
#include <sys/sysent.h>
#include <sys/reboot.h>
#include <sys/sysproto.h>
#include <sys/vmmeter.h>
#include <sys/unistd.h>
#include <sys/malloc.h>
#include <machine/cpu.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_prot.h>
#include <sys/lock.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <sys/user.h>
#include <sys/copyright.h>
extern struct linker_set sysinit_set; /* XXX */
extern void __main __P((void));
extern void main __P((void *framep));
/* Components of the first process -- never freed. */
static struct session session0;
static struct pgrp pgrp0;
struct proc proc0;
static struct pcred cred0;
static struct filedesc0 filedesc0;
static struct plimit limit0;
static struct vmspace vmspace0;
struct proc *initproc;
int cmask = CMASK;
extern struct user *proc0paddr;
struct vnode *rootvp;
int boothowto = 0; /* initialized so that it can be patched */
struct timeval boottime;
SYSCTL_STRUCT(_kern, KERN_BOOTTIME, boottime,
CTLFLAG_RD, &boottime, timeval, "");
static int shutdowntimeout = 120;
SYSCTL_INT(_kern, OID_AUTO, shutdown_timeout,
CTLFLAG_RW, &shutdowntimeout, 0, "");
/*
* Promiscuous argument pass for start_init()
*
* This is a kludge because we use a return from main() rather than a call
* to a new routine in locore.s to kick the kernel alive from locore.s.
*/
static void *init_framep;
#if __GNUC__ >= 2
void __main() {}
#endif
/*
* This ensures that there is at least one entry so that the sysinit_set
* symbol is not undefined. A sybsystem ID of SI_SUB_DUMMY is never
* executed.
*/
SYSINIT(placeholder, SI_SUB_DUMMY,SI_ORDER_ANY, NULL, NULL)
/*
* The sysinit table itself. Items are checked off as the are run.
* If we want to register new sysinit types, add them to newsysinit.
*/
struct sysinit **sysinit = (struct sysinit **)sysinit_set.ls_items;
struct sysinit **newsysinit;
/*
* Merge a new sysinit set into the current set, reallocating it if
* necessary. This can only be called after malloc is running.
*/
void
sysinit_add(set)
struct sysinit **set;
{
struct sysinit **newset;
struct sysinit **sipp;
struct sysinit **xipp;
int count = 0;
if (newsysinit)
for (sipp = newsysinit; *sipp; sipp++)
count++;
else
for (sipp = sysinit; *sipp; sipp++)
count++;
for (sipp = set; *sipp; sipp++)
count++;
count++; /* Trailing NULL */
newset = malloc(count * sizeof(*sipp), M_TEMP, M_NOWAIT);
if (newset == NULL)
panic("cannot malloc for sysinit");
xipp = newset;
if (newsysinit)
for (sipp = newsysinit; *sipp; sipp++)
*xipp++ = *sipp;
else
for (sipp = sysinit; *sipp; sipp++)
*xipp++ = *sipp;
for (sipp = set; *sipp; sipp++)
*xipp++ = *sipp;
*xipp = NULL;
if (newsysinit)
free(newsysinit, M_TEMP);
newsysinit = newset;
}
/*
* System startup; initialize the world, create process 0, mount root
* filesystem, and fork to create init and pagedaemon. Most of the
* hard work is done in the lower-level initialization routines including
* startup(), which does memory initialization and autoconfiguration.
*
* This allows simple addition of new kernel subsystems that require
* boot time initialization. It also allows substitution of subsystem
* (for instance, a scheduler, kernel profiler, or VM system) by object
* module. Finally, it allows for optional "kernel threads".
*/
void
main(framep)
void *framep;
{
register struct sysinit **sipp; /* system initialization*/
register struct sysinit **xipp; /* interior loop of sort*/
register struct sysinit *save; /* bubble*/
/*
* Copy the locore.s frame pointer for proc0, this is forked into
* all other processes.
*/
init_framep = framep;
restart:
/*
* Perform a bubble sort of the system initialization objects by
* their subsystem (primary key) and order (secondary key).
*/
for (sipp = sysinit; *sipp; sipp++) {
for (xipp = sipp + 1; *xipp; xipp++) {
if ((*sipp)->subsystem < (*xipp)->subsystem ||
((*sipp)->subsystem == (*xipp)->subsystem &&
(*sipp)->order < (*xipp)->order))
continue; /* skip*/
save = *sipp;
*sipp = *xipp;
*xipp = save;
}
}
/*
* Traverse the (now) ordered list of system initialization tasks.
* Perform each task, and continue on to the next task.
*
* The last item on the list is expected to be the scheduler,
* which will not return.
*/
for (sipp = sysinit; *sipp; sipp++) {
if ((*sipp)->subsystem == SI_SUB_DUMMY)
continue; /* skip dummy task(s)*/
if ((*sipp)->subsystem == SI_SUB_DONE)
continue;
switch( (*sipp)->type) {
case SI_TYPE_DEFAULT:
/* no special processing*/
(*((*sipp)->func))((*sipp)->udata);
break;
case SI_TYPE_KTHREAD:
#if !defined(SMP)
/* kernel thread*/
if (fork1(&proc0, RFMEM|RFFDG|RFPROC))
panic("fork kernel thread");
cpu_set_fork_handler(pfind(proc0.p_retval[0]),
(*sipp)->func, (*sipp)->udata);
break;
#endif
case SI_TYPE_KPROCESS:
if (fork1(&proc0, RFFDG|RFPROC))
panic("fork kernel process");
cpu_set_fork_handler(pfind(proc0.p_retval[0]),
(*sipp)->func, (*sipp)->udata);
break;
default:
panic("init_main: unrecognized init type");
}
/* Check off the one we're just done */
(*sipp)->subsystem = SI_SUB_DONE;
/* Check if we've installed more sysinit items via KLD */
if (newsysinit != NULL) {
if (sysinit != (struct sysinit **)sysinit_set.ls_items)
free(sysinit, M_TEMP);
sysinit = newsysinit;
newsysinit = NULL;
goto restart;
}
}
panic("Shouldn't get here!");
/* NOTREACHED*/
}
/*
* Start a kernel process. This is called after a fork() call in
* main() in the file kern/init_main.c.
*
* This function is used to start "internal" daemons.
*/
/* ARGSUSED*/
void
kproc_start(udata)
void *udata;
{
struct kproc_desc *kp = udata;
struct proc *p = curproc;
#ifdef DIAGNOSTIC
printf("Start pid=%d <%s>\n",p->p_pid, kp->arg0);
#endif
/* save a global descriptor, if desired*/
if( kp->global_procpp != NULL)
*kp->global_procpp = p;
/* this is a non-swapped system process*/
p->p_flag |= P_INMEM | P_SYSTEM;
/* set up arg0 for 'ps', et al*/
strcpy( p->p_comm, kp->arg0);
/* call the processes' main()...*/
(*kp->func)();
/* NOTREACHED */
panic("kproc_start: %s", kp->arg0);
}
/*
***************************************************************************
****
**** The following SYSINIT's belong elsewhere, but have not yet
**** been moved.
****
***************************************************************************
*/
#ifdef OMIT
/*
* Handled by vfs_mountroot (bad idea) at this time... should be
* done the same as 4.4Lite2.
*/
SYSINIT(swapinit, SI_SUB_SWAP, SI_ORDER_FIRST, swapinit, NULL)
#endif /* OMIT*/
static void print_caddr_t __P((void *data));
static void
print_caddr_t(data)
void *data;
{
printf("%s", (char *)data);
}
SYSINIT(announce, SI_SUB_COPYRIGHT, SI_ORDER_FIRST, print_caddr_t, copyright)
/*
***************************************************************************
****
**** The two following SYSINT's are proc0 specific glue code. I am not
**** convinced that they can not be safely combined, but their order of
**** operation has been maintained as the same as the original init_main.c
**** for right now.
****
**** These probably belong in init_proc.c or kern_proc.c, since they
**** deal with proc0 (the fork template process).
****
***************************************************************************
*/
/* ARGSUSED*/
static void proc0_init __P((void *dummy));
static void
proc0_init(dummy)
void *dummy;
{
register struct proc *p;
register struct filedesc0 *fdp;
register unsigned i;
/*
* Initialize the current process pointer (curproc) before
* any possible traps/probes to simplify trap processing.
*/
p = &proc0;
curproc = p; /* XXX redundant*/
/*
* Initialize process and pgrp structures.
*/
procinit();
/*
* Initialize sleep queue hash table
*/
sleepinit();
/*
* additional VM structures
*/
vm_init2();
/*
* Create process 0 (the swapper).
*/
LIST_INSERT_HEAD(&allproc, p, p_list);
p->p_pgrp = &pgrp0;
LIST_INSERT_HEAD(PGRPHASH(0), &pgrp0, pg_hash);
LIST_INIT(&pgrp0.pg_members);
LIST_INSERT_HEAD(&pgrp0.pg_members, p, p_pglist);
pgrp0.pg_session = &session0;
session0.s_count = 1;
session0.s_leader = p;
p->p_sysent = &aout_sysvec;
p->p_flag = P_INMEM | P_SYSTEM;
p->p_stat = SRUN;
p->p_nice = NZERO;
p->p_rtprio.type = RTP_PRIO_NORMAL;
p->p_rtprio.prio = 0;
/*
* Link for kernel based threads
*/
p->p_peers = 0;
p->p_leader = p;
bcopy("swapper", p->p_comm, sizeof ("swapper"));
/* Create credentials. */
cred0.p_refcnt = 1;
p->p_cred = &cred0;
p->p_ucred = crget();
p->p_ucred->cr_ngroups = 1; /* group 0 */
/* Create the file descriptor table. */
fdp = &filedesc0;
p->p_fd = &fdp->fd_fd;
fdp->fd_fd.fd_refcnt = 1;
fdp->fd_fd.fd_cmask = cmask;
fdp->fd_fd.fd_ofiles = fdp->fd_dfiles;
fdp->fd_fd.fd_ofileflags = fdp->fd_dfileflags;
fdp->fd_fd.fd_nfiles = NDFILE;
/* Create the limits structures. */
p->p_limit = &limit0;
for (i = 0; i < sizeof(p->p_rlimit)/sizeof(p->p_rlimit[0]); i++)
limit0.pl_rlimit[i].rlim_cur =
limit0.pl_rlimit[i].rlim_max = RLIM_INFINITY;
limit0.pl_rlimit[RLIMIT_NOFILE].rlim_cur =
limit0.pl_rlimit[RLIMIT_NOFILE].rlim_max = maxfiles;
limit0.pl_rlimit[RLIMIT_NPROC].rlim_cur =
limit0.pl_rlimit[RLIMIT_NPROC].rlim_max = maxproc;
i = ptoa(cnt.v_free_count);
limit0.pl_rlimit[RLIMIT_RSS].rlim_max = i;
limit0.pl_rlimit[RLIMIT_MEMLOCK].rlim_max = i;
limit0.pl_rlimit[RLIMIT_MEMLOCK].rlim_cur = i / 3;
limit0.p_cpulimit = RLIM_INFINITY;
limit0.p_refcnt = 1;
/* Allocate a prototype map so we have something to fork. */
pmap_pinit0(&vmspace0.vm_pmap);
p->p_vmspace = &vmspace0;
vmspace0.vm_refcnt = 1;
vm_map_init(&vmspace0.vm_map, round_page(VM_MIN_ADDRESS),
trunc_page(VM_MAXUSER_ADDRESS));
vmspace0.vm_map.pmap = &vmspace0.vm_pmap;
p->p_addr = proc0paddr; /* XXX */
#ifndef __alpha__ /* XXX what is this? */
#define INCOMPAT_LITES2
#ifdef INCOMPAT_LITES2
/*
* proc0 needs to have a coherent frame base in its stack.
*/
cpu_set_init_frame(p, init_framep); /* XXX! */
#endif /* INCOMPAT_LITES2*/
#endif
/*
* We continue to place resource usage info and signal
* actions in the user struct so they're pageable.
*/
p->p_stats = &p->p_addr->u_stats;
p->p_sigacts = &p->p_addr->u_sigacts;
/*
* Charge root for one process.
*/
(void)chgproccnt(0, 1);
/*
* Initialize the procfs flags (to 0, of course)
*/
p->p_stops = p->p_stype = p->p_step = 0;
}
SYSINIT(p0init, SI_SUB_INTRINSIC, SI_ORDER_FIRST, proc0_init, NULL)
/* ARGSUSED*/
static void proc0_post __P((void *dummy));
static void
proc0_post(dummy)
void *dummy;
{
struct timespec ts;
/*
* Now can look at time, having had a chance to verify the time
* from the file system. Reset p->p_runtime as it may have been
* munched in mi_switch() after the time got set. Set
* p->p_switchtime to be consistent with this unmunching.
*/
microtime(&proc0.p_stats->p_start);
proc0.p_runtime = 0;
microuptime(&proc0.p_switchtime);
/*
* Give the ``random'' number generator a thump.
* XXX: Does read_random() contain enough bits to be used here ?
*/
nanotime(&ts);
srandom(ts.tv_sec ^ ts.tv_nsec);
/* Initialize signal state for process 0. */
siginit(&proc0);
}
SYSINIT(p0post, SI_SUB_INTRINSIC_POST, SI_ORDER_FIRST, proc0_post, NULL)
/*
***************************************************************************
****
**** The following SYSINIT's and glue code should be moved to the
**** respective files on a per subsystem basis.
****
***************************************************************************
*/
/* ARGSUSED */
static void root_conf __P((void *dummy));
static void
root_conf(dummy)
void *dummy;
{
cpu_rootconf();
}
SYSINIT(root_conf, SI_SUB_ROOT_CONF, SI_ORDER_FIRST, root_conf, NULL)
/* ARGSUSED*/
static void xxx_vfs_root_fdtab __P((void *dummy));
static void
xxx_vfs_root_fdtab(dummy)
void *dummy;
{
register struct filedesc0 *fdp = &filedesc0;
/* Get the vnode for '/'. Set fdp->fd_fd.fd_cdir to reference it. */
if (VFS_ROOT(mountlist.cqh_first, &rootvnode))
panic("cannot find root vnode");
fdp->fd_fd.fd_cdir = rootvnode;
VREF(fdp->fd_fd.fd_cdir);
VOP_UNLOCK(rootvnode, 0, &proc0);
fdp->fd_fd.fd_rdir = rootvnode;
}
SYSINIT(retrofit, SI_SUB_ROOT_FDTAB, SI_ORDER_FIRST, xxx_vfs_root_fdtab, NULL)
/*
***************************************************************************
****
**** The following code probably belongs in another file, like
**** kern/init_init.c. It is here for two reasons only:
****
**** 1) This code returns to startup the system; this is
**** abnormal for a kernel thread.
**** 2) This code promiscuously uses init_frame
****
***************************************************************************
*/
static void kthread_init __P((void *dummy));
SYSINIT_KP(init,SI_SUB_KTHREAD_INIT, SI_ORDER_FIRST, kthread_init, NULL)
extern void prepare_usermode __P((void));
static void start_init __P((struct proc *p));
/* ARGSUSED*/
static void
kthread_init(dummy)
void *dummy;
{
/* Create process 1 (init(8)). */
start_init(curproc);
prepare_usermode();
/*
* This returns to the fork trampoline, then to user mode.
*/
return;
}
/*
* List of paths to try when searching for "init".
*/
static char *initpaths[] = {
"/sbin/init",
"/sbin/oinit",
"/sbin/init.bak",
"/stand/sysinstall",
NULL,
};
/*
* Start the initial user process; try exec'ing each pathname in "initpaths".
* The program is invoked with one argument containing the boot flags.
*/
static void
start_init(p)
struct proc *p;
{
vm_offset_t addr;
struct execve_args args;
int options, i, error;
char **pathp, *path, *ucp, **uap, *arg0, *arg1;
initproc = p;
/*
* Need just enough stack to hold the faked-up "execve()" arguments.
*/
addr = trunc_page(VM_MAXUSER_ADDRESS - PAGE_SIZE);
if (vm_map_find(&p->p_vmspace->vm_map, NULL, 0, &addr, PAGE_SIZE, FALSE, VM_PROT_ALL, VM_PROT_ALL, 0) != 0)
panic("init: couldn't allocate argument space");
p->p_vmspace->vm_maxsaddr = (caddr_t)addr;
p->p_vmspace->vm_ssize = 1;
for (pathp = &initpaths[0]; (path = *pathp) != NULL; pathp++) {
/*
* Move out the boot flag argument.
*/
options = 0;
ucp = (char *)USRSTACK;
(void)subyte(--ucp, 0); /* trailing zero */
if (boothowto & RB_SINGLE) {
(void)subyte(--ucp, 's');
options = 1;
}
#ifdef notyet
if (boothowto & RB_FASTBOOT) {
(void)subyte(--ucp, 'f');
options = 1;
}
#endif
#ifdef BOOTCDROM
(void)subyte(--ucp, 'C');
options = 1;
#endif
if (options == 0)
(void)subyte(--ucp, '-');
(void)subyte(--ucp, '-'); /* leading hyphen */
arg1 = ucp;
/*
* Move out the file name (also arg 0).
*/
for (i = strlen(path) + 1; i >= 0; i--)
(void)subyte(--ucp, path[i]);
arg0 = ucp;
/*
* Move out the arg pointers.
*/
uap = (char **)((intptr_t)ucp & ~(sizeof(intptr_t)-1));
(void)suword((caddr_t)--uap, (long)0); /* terminator */
(void)suword((caddr_t)--uap, (long)(intptr_t)arg1);
(void)suword((caddr_t)--uap, (long)(intptr_t)arg0);
/*
* Point at the arguments.
*/
args.fname = arg0;
args.argv = uap;
args.envv = NULL;
/*
* Now try to exec the program. If can't for any reason
* other than it doesn't exist, complain.
*
* Otherwise return to main() which returns to btext
* which completes the system startup.
*/
if ((error = execve(p, &args)) == 0)
return;
if (error != ENOENT)
printf("exec %s: error %d\n", path, error);
}
printf("init: not found\n");
panic("no init");
}
|