freebsd-nq/sys/kern/init_main.c

762 lines
20 KiB
C
Raw Normal View History

/*-
* Copyright (c) 1995 Terrence R. Lambert
* All rights reserved.
*
1994-05-24 10:09:53 +00:00
* 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
*/
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ddb.h"
#include "opt_init_path.h"
#include "opt_mac.h"
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/exec.h>
#include <sys/file.h>
1994-05-24 10:09:53 +00:00
#include <sys/filedesc.h>
#include <sys/ktr.h>
#include <sys/lock.h>
#include <sys/mount.h>
#include <sys/mutex.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
1994-05-24 10:09:53 +00:00
#include <sys/proc.h>
#include <sys/resourcevar.h>
#include <sys/systm.h>
#include <sys/signalvar.h>
1994-05-24 10:09:53 +00:00
#include <sys/vnode.h>
#include <sys/sysent.h>
1994-05-24 10:09:53 +00:00
#include <sys/reboot.h>
#include <sys/sched.h>
#include <sys/sx.h>
#include <sys/sysproto.h>
#include <sys/vmmeter.h>
#include <sys/unistd.h>
#include <sys/malloc.h>
#include <sys/conf.h>
1994-05-24 10:09:53 +00:00
#include <machine/cpu.h>
#include <security/audit/audit.h>
#include <security/mac/mac_framework.h>
1994-05-24 10:09:53 +00:00
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <sys/copyright.h>
1994-05-24 10:09:53 +00:00
#include <ddb/ddb.h>
#include <ddb/db_sym.h>
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
void mi_startup(void); /* Should be elsewhere */
1994-05-24 10:09:53 +00:00
/* Components of the first process -- never freed. */
static struct session session0;
static struct pgrp pgrp0;
1994-05-24 10:09:53 +00:00
struct proc proc0;
struct thread thread0 __aligned(16);
struct vmspace vmspace0;
struct proc *initproc;
1994-05-24 10:09:53 +00:00
int boothowto = 0; /* initialized so that it can be patched */
SYSCTL_INT(_debug, OID_AUTO, boothowto, CTLFLAG_RD, &boothowto, 0, "");
int bootverbose;
SYSCTL_INT(_debug, OID_AUTO, bootverbose, CTLFLAG_RW, &bootverbose, 0, "");
/*
* 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.
*/
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
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.
*/
SET_DECLARE(sysinit_set, struct sysinit);
struct sysinit **sysinit, **sysinit_end;
struct sysinit **newsysinit, **newsysinit_end;
/*
* 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(struct sysinit **set, struct sysinit **set_end)
{
struct sysinit **newset;
struct sysinit **sipp;
struct sysinit **xipp;
int count;
count = set_end - set;
if (newsysinit)
count += newsysinit_end - newsysinit;
else
count += sysinit_end - sysinit;
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 < newsysinit_end; sipp++)
*xipp++ = *sipp;
else
for (sipp = sysinit; sipp < sysinit_end; sipp++)
*xipp++ = *sipp;
for (sipp = set; sipp < set_end; sipp++)
*xipp++ = *sipp;
if (newsysinit)
free(newsysinit, M_TEMP);
newsysinit = newset;
newsysinit_end = newset + count;
}
1994-05-24 10:09:53 +00:00
/*
* 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".
1994-05-24 10:09:53 +00:00
*/
void
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
mi_startup(void)
1994-05-24 10:09:53 +00:00
{
register struct sysinit **sipp; /* system initialization*/
register struct sysinit **xipp; /* interior loop of sort*/
register struct sysinit *save; /* bubble*/
#if defined(VERBOSE_SYSINIT)
int last;
int verbose;
#endif
if (sysinit == NULL) {
sysinit = SET_BEGIN(sysinit_set);
sysinit_end = SET_LIMIT(sysinit_set);
}
restart:
/*
* Perform a bubble sort of the system initialization objects by
* their subsystem (primary key) and order (secondary key).
*/
for (sipp = sysinit; sipp < sysinit_end; sipp++) {
for (xipp = sipp + 1; xipp < sysinit_end; xipp++) {
if ((*sipp)->subsystem < (*xipp)->subsystem ||
((*sipp)->subsystem == (*xipp)->subsystem &&
(*sipp)->order <= (*xipp)->order))
continue; /* skip*/
save = *sipp;
*sipp = *xipp;
*xipp = save;
}
}
#if defined(VERBOSE_SYSINIT)
last = SI_SUB_COPYRIGHT;
verbose = 0;
#if !defined(DDB)
printf("VERBOSE_SYSINIT: DDB not enabled, symbol lookups disabled.\n");
#endif
#endif
/*
* 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 < sysinit_end; sipp++) {
if ((*sipp)->subsystem == SI_SUB_DUMMY)
continue; /* skip dummy task(s)*/
if ((*sipp)->subsystem == SI_SUB_DONE)
continue;
#if defined(VERBOSE_SYSINIT)
if ((*sipp)->subsystem > last) {
verbose = 1;
last = (*sipp)->subsystem;
printf("subsystem %x\n", last);
}
if (verbose) {
#if defined(DDB)
const char *name;
c_db_sym_t sym;
db_expr_t offset;
sym = db_search_symbol((vm_offset_t)(*sipp)->func,
DB_STGY_PROC, &offset);
db_symbol_values(sym, &name, NULL);
if (name != NULL)
printf(" %s(%p)... ", name, (*sipp)->udata);
else
#endif
printf(" %p(%p)... ", (*sipp)->func,
(*sipp)->udata);
}
#endif
/* Call function */
(*((*sipp)->func))((*sipp)->udata);
#if defined(VERBOSE_SYSINIT)
if (verbose)
printf("done.\n");
#endif
/* 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 != SET_BEGIN(sysinit_set))
free(sysinit, M_TEMP);
sysinit = newsysinit;
sysinit_end = newsysinit_end;
newsysinit = NULL;
newsysinit_end = NULL;
goto restart;
}
}
panic("Shouldn't get here!");
/* NOTREACHED*/
}
/*
***************************************************************************
****
**** The following SYSINIT's belong elsewhere, but have not yet
**** been moved.
****
***************************************************************************
*/
static void
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
print_caddr_t(void *data __unused)
{
printf("%s", (char *)data);
}
SYSINIT(announce, SI_SUB_COPYRIGHT, SI_ORDER_FIRST, print_caddr_t, copyright)
SYSINIT(trademark, SI_SUB_COPYRIGHT, SI_ORDER_SECOND, print_caddr_t, trademark)
SYSINIT(version, SI_SUB_COPYRIGHT, SI_ORDER_THIRD, print_caddr_t, version)
#ifdef WITNESS
static char wit_warn[] =
"WARNING: WITNESS option enabled, expect reduced performance.\n";
SYSINIT(witwarn, SI_SUB_COPYRIGHT, SI_ORDER_THIRD + 1,
print_caddr_t, wit_warn)
SYSINIT(witwarn2, SI_SUB_RUN_SCHEDULER, SI_ORDER_THIRD + 1,
print_caddr_t, wit_warn)
#endif
#ifdef DIAGNOSTIC
static char diag_warn[] =
"WARNING: DIAGNOSTIC option enabled, expect reduced performance.\n";
SYSINIT(diagwarn, SI_SUB_COPYRIGHT, SI_ORDER_THIRD + 2,
print_caddr_t, diag_warn)
SYSINIT(diagwarn2, SI_SUB_RUN_SCHEDULER, SI_ORDER_THIRD + 2,
print_caddr_t, diag_warn)
#endif
static void
set_boot_verbose(void *data __unused)
{
if (boothowto & RB_VERBOSE)
bootverbose++;
}
SYSINIT(boot_verbose, SI_SUB_TUNABLES, SI_ORDER_ANY, set_boot_verbose, NULL)
struct sysentvec null_sysvec = {
0,
NULL,
0,
0,
NULL,
0,
NULL,
NULL,
NULL,
NULL,
NULL,
NULL,
NULL,
"null",
NULL,
NULL,
0,
PAGE_SIZE,
VM_MIN_ADDRESS,
VM_MAXUSER_ADDRESS,
USRSTACK,
PS_STRINGS,
VM_PROT_ALL,
NULL,
NULL,
NULL
};
/*
***************************************************************************
****
**** The two following SYSINIT'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
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
proc0_init(void *dummy __unused)
{
struct proc *p;
unsigned i;
struct thread *td;
1994-05-24 10:09:53 +00:00
GIANT_REQUIRED;
1994-05-24 10:09:53 +00:00
p = &proc0;
td = &thread0;
/*
* Initialize magic number and osrel.
*/
p->p_magic = P_MAGIC;
p->p_osrel = osreldate;
/*
* Initialize thread and process structures.
*/
procinit(); /* set up proc zone */
threadinit(); /* set up UMA zones */
/*
* Initialise scheduler resources.
* Add scheduler specific parts to proc, thread as needed.
*/
Refactor a bunch of scheduler code to give basically the same behaviour but with slightly cleaned up interfaces. The KSE structure has become the same as the "per thread scheduler private data" structure. In order to not make the diffs too great one is #defined as the other at this time. The KSE (or td_sched) structure is now allocated per thread and has no allocation code of its own. Concurrency for a KSEGRP is now kept track of via a simple pair of counters rather than using KSE structures as tokens. Since the KSE structure is different in each scheduler, kern_switch.c is now included at the end of each scheduler. Nothing outside the scheduler knows the contents of the KSE (aka td_sched) structure. The fields in the ksegrp structure that are to do with the scheduler's queueing mechanisms are now moved to the kg_sched structure. (per ksegrp scheduler private data structure). In other words how the scheduler queues and keeps track of threads is no-one's business except the scheduler's. This should allow people to write experimental schedulers with completely different internal structuring. A scheduler call sched_set_concurrency(kg, N) has been added that notifies teh scheduler that no more than N threads from that ksegrp should be allowed to be on concurrently scheduled. This is also used to enforce 'fainess' at this time so that a ksegrp with 10000 threads can not swamp a the run queue and force out a process with 1 thread, since the current code will not set the concurrency above NCPU, and both schedulers will not allow more than that many onto the system run queue at a time. Each scheduler should eventualy develop their own methods to do this now that they are effectively separated. Rejig libthr's kernel interface to follow the same code paths as linkse for scope system threads. This has slightly hurt libthr's performance but I will work to recover as much of it as I can. Thread exit code has been cleaned up greatly. exit and exec code now transitions a process back to 'standard non-threaded mode' before taking the next step. Reviewed by: scottl, peter MFC after: 1 week
2004-09-05 02:09:54 +00:00
schedinit(); /* scheduler gets its house in order */
/*
* Initialize sleep queue hash table
*/
sleepinit();
/*
* additional VM structures
*/
vm_init2();
1994-05-24 10:09:53 +00:00
/*
* Create process 0 (the swapper).
*/
LIST_INSERT_HEAD(&allproc, p, p_list);
2001-04-11 18:50:50 +00:00
LIST_INSERT_HEAD(PIDHASH(0), p, p_hash);
mtx_init(&pgrp0.pg_mtx, "process group", NULL, MTX_DEF | MTX_DUPOK);
1994-05-24 10:09:53 +00:00
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);
1994-05-24 10:09:53 +00:00
pgrp0.pg_session = &session0;
mtx_init(&session0.s_mtx, "session", NULL, MTX_DEF);
1994-05-24 10:09:53 +00:00
session0.s_count = 1;
session0.s_leader = p;
p->p_sysent = &null_sysvec;
p->p_flag = P_SYSTEM | P_INMEM;
p->p_state = PRS_NORMAL;
knlist_init(&p->p_klist, &p->p_mtx, NULL, NULL, NULL);
Moderate rewrite of kernel ktrace code to attempt to generally improve reliability when tracing fast-moving processes or writing traces to slow file systems by avoiding unbounded queueuing and dropped records. Record loss was previously possible when the global pool of records become depleted as a result of record generation outstripping record commit, which occurred quickly in many common situations. These changes partially restore the 4.x model of committing ktrace records at the point of trace generation (synchronous), but maintain the 5.x deferred record commit behavior (asynchronous) for situations where entering VFS and sleeping is not possible (i.e., in the scheduler). Records are now queued per-process as opposed to globally, with processes responsible for committing records from their own context as required. - Eliminate the ktrace worker thread and global record queue, as they are no longer used. Keep the global free record list, as records are still used. - Add a per-process record queue, which will hold any asynchronously generated records, such as from context switches. This replaces the global queue as the place to submit asynchronous records to. - When a record is committed asynchronously, simply queue it to the process. - When a record is committed synchronously, first drain any pending per-process records in order to maintain ordering as best we can. Currently ordering between competing threads is provided via a global ktrace_sx, but a per-process flag or lock may be desirable in the future. - When a process returns to user space following a system call, trap, signal delivery, etc, flush any pending records. - When a process exits, flush any pending records. - Assert on process tear-down that there are no pending records. - Slightly abstract the notion of being "in ktrace", which is used to prevent the recursive generation of records, as well as generating traces for ktrace events. Future work here might look at changing the set of events marked for synchronous and asynchronous record generation, re-balancing queue depth, timeliness of commit to disk, and so on. I.e., performing a drain every (n) records. MFC after: 1 month Discussed with: jhb Requested by: Marc Olzheim <marcolz at stack dot nl>
2005-11-13 13:27:44 +00:00
STAILQ_INIT(&p->p_ktr);
p->p_nice = NZERO;
td->td_tid = PID_MAX + 1;
td->td_state = TDS_RUNNING;
td->td_pri_class = PRI_TIMESHARE;
td->td_user_pri = PUSER;
td->td_base_user_pri = PUSER;
td->td_priority = PVM;
td->td_base_pri = PUSER;
td->td_oncpu = 0;
td->td_flags = TDF_INMEM|TDP_KTHREAD;
p->p_peers = 0;
p->p_leader = p;
strncpy(p->p_comm, "kernel", sizeof (p->p_comm));
strncpy(td->td_name, "swapper", sizeof (td->td_name));
1994-05-24 10:09:53 +00:00
callout_init(&p->p_itcallout, CALLOUT_MPSAFE);
callout_init_mtx(&p->p_limco, &p->p_mtx, 0);
callout_init(&td->td_slpcallout, CALLOUT_MPSAFE);
1994-05-24 10:09:53 +00:00
/* Create credentials. */
p->p_ucred = crget();
p->p_ucred->cr_ngroups = 1; /* group 0 */
p->p_ucred->cr_uidinfo = uifind(0);
o Merge contents of struct pcred into struct ucred. Specifically, add the real uid, saved uid, real gid, and saved gid to ucred, as well as the pcred->pc_uidinfo, which was associated with the real uid, only rename it to cr_ruidinfo so as not to conflict with cr_uidinfo, which corresponds to the effective uid. o Remove p_cred from struct proc; add p_ucred to struct proc, replacing original macro that pointed. p->p_ucred to p->p_cred->pc_ucred. o Universally update code so that it makes use of ucred instead of pcred, p->p_ucred instead of p->p_pcred, cr_ruidinfo instead of p_uidinfo, cr_{r,sv}{u,g}id instead of p_*, etc. o Remove pcred0 and its initialization from init_main.c; initialize cr_ruidinfo there. o Restruction many credential modification chunks to always crdup while we figure out locking and optimizations; generally speaking, this means moving to a structure like this: newcred = crdup(oldcred); ... p->p_ucred = newcred; crfree(oldcred); It's not race-free, but better than nothing. There are also races in sys_process.c, all inter-process authorization, fork, exec, and exit. o Remove sigio->sio_ruid since sigio->sio_ucred now contains the ruid; remove comments indicating that the old arrangement was a problem. o Restructure exec1() a little to use newcred/oldcred arrangement, and use improved uid management primitives. o Clean up exit1() so as to do less work in credential cleanup due to pcred removal. o Clean up fork1() so as to do less work in credential cleanup and allocation. o Clean up ktrcanset() to take into account changes, and move to using suser_xxx() instead of performing a direct uid==0 comparision. o Improve commenting in various kern_prot.c credential modification calls to better document current behavior. In a couple of places, current behavior is a little questionable and we need to check POSIX.1 to make sure it's "right". More commenting work still remains to be done. o Update credential management calls, such as crfree(), to take into account new ruidinfo reference. o Modify or add the following uid and gid helper routines: change_euid() change_egid() change_ruid() change_rgid() change_svuid() change_svgid() In each case, the call now acts on a credential not a process, and as such no longer requires more complicated process locking/etc. They now assume the caller will do any necessary allocation of an exclusive credential reference. Each is commented to document its reference requirements. o CANSIGIO() is simplified to require only credentials, not processes and pcreds. o Remove lots of (p_pcred==NULL) checks. o Add an XXX to authorization code in nfs_lock.c, since it's questionable, and needs to be considered carefully. o Simplify posix4 authorization code to require only credentials, not processes and pcreds. Note that this authorization, as well as CANSIGIO(), needs to be updated to use the p_cansignal() and p_cansched() centralized authorization routines, as they currently do not take into account some desirable restrictions that are handled by the centralized routines, as well as being inconsistent with other similar authorization instances. o Update libkvm to take these changes into account. Obtained from: TrustedBSD Project Reviewed by: green, bde, jhb, freebsd-arch, freebsd-audit
2001-05-25 16:59:11 +00:00
p->p_ucred->cr_ruidinfo = uifind(0);
p->p_ucred->cr_prison = NULL; /* Don't jail it. */
#ifdef AUDIT
audit_cred_kproc0(p->p_ucred);
#endif
#ifdef MAC
mac_proc_create_swapper(p->p_ucred);
#endif
td->td_ucred = crhold(p->p_ucred);
This Implements the mumbled about "Jail" feature. This is a seriously beefed up chroot kind of thing. The process is jailed along the same lines as a chroot does it, but with additional tough restrictions imposed on what the superuser can do. For all I know, it is safe to hand over the root bit inside a prison to the customer living in that prison, this is what it was developed for in fact: "real virtual servers". Each prison has an ip number associated with it, which all IP communications will be coerced to use and each prison has its own hostname. Needless to say, you need more RAM this way, but the advantage is that each customer can run their own particular version of apache and not stomp on the toes of their neighbors. It generally does what one would expect, but setting up a jail still takes a little knowledge. A few notes: I have no scripts for setting up a jail, don't ask me for them. The IP number should be an alias on one of the interfaces. mount a /proc in each jail, it will make ps more useable. /proc/<pid>/status tells the hostname of the prison for jailed processes. Quotas are only sensible if you have a mountpoint per prison. There are no privisions for stopping resource-hogging. Some "#ifdef INET" and similar may be missing (send patches!) If somebody wants to take it from here and develop it into more of a "virtual machine" they should be most welcome! Tools, comments, patches & documentation most welcome. Have fun... Sponsored by: http://www.rndassociates.com/ Run for almost a year by: http://www.servetheweb.com/
1999-04-28 11:38:52 +00:00
/* Create sigacts. */
p->p_sigacts = sigacts_alloc();
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
/* Initialize signal state for process 0. */
siginit(&proc0);
1994-05-24 10:09:53 +00:00
/* Create the file descriptor table. */
p->p_fd = fdinit(NULL);
p->p_fdtol = NULL;
1994-05-24 10:09:53 +00:00
/* Create the limits structures. */
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
p->p_limit = lim_alloc();
for (i = 0; i < RLIM_NLIMITS; i++)
p->p_limit->pl_rlimit[i].rlim_cur =
p->p_limit->pl_rlimit[i].rlim_max = RLIM_INFINITY;
p->p_limit->pl_rlimit[RLIMIT_NOFILE].rlim_cur =
p->p_limit->pl_rlimit[RLIMIT_NOFILE].rlim_max = maxfiles;
p->p_limit->pl_rlimit[RLIMIT_NPROC].rlim_cur =
p->p_limit->pl_rlimit[RLIMIT_NPROC].rlim_max = maxproc;
i = ptoa(cnt.v_free_count);
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
p->p_limit->pl_rlimit[RLIMIT_RSS].rlim_max = i;
p->p_limit->pl_rlimit[RLIMIT_MEMLOCK].rlim_max = i;
p->p_limit->pl_rlimit[RLIMIT_MEMLOCK].rlim_cur = i / 3;
p->p_cpulimit = RLIM_INFINITY;
1994-05-24 10:09:53 +00:00
p->p_stats = pstats_alloc();
1994-05-24 10:09:53 +00:00
/* Allocate a prototype map so we have something to fork. */
pmap_pinit0(vmspace_pmap(&vmspace0));
1994-05-24 10:09:53 +00:00
p->p_vmspace = &vmspace0;
vmspace0.vm_refcnt = 1;
vm_map_init(&vmspace0.vm_map, p->p_sysent->sv_minuser,
p->p_sysent->sv_maxuser);
vmspace0.vm_map.pmap = vmspace_pmap(&vmspace0);
1994-05-24 10:09:53 +00:00
/*-
* call the init and ctor for the new thread and proc
* we wait to do this until all other structures
* are fairly sane.
*/
EVENTHANDLER_INVOKE(process_init, p);
EVENTHANDLER_INVOKE(thread_init, td);
EVENTHANDLER_INVOKE(process_ctor, p);
EVENTHANDLER_INVOKE(thread_ctor, td);
1994-05-24 10:09:53 +00:00
/*
* Charge root for one process.
1994-05-24 10:09:53 +00:00
*/
o Merge contents of struct pcred into struct ucred. Specifically, add the real uid, saved uid, real gid, and saved gid to ucred, as well as the pcred->pc_uidinfo, which was associated with the real uid, only rename it to cr_ruidinfo so as not to conflict with cr_uidinfo, which corresponds to the effective uid. o Remove p_cred from struct proc; add p_ucred to struct proc, replacing original macro that pointed. p->p_ucred to p->p_cred->pc_ucred. o Universally update code so that it makes use of ucred instead of pcred, p->p_ucred instead of p->p_pcred, cr_ruidinfo instead of p_uidinfo, cr_{r,sv}{u,g}id instead of p_*, etc. o Remove pcred0 and its initialization from init_main.c; initialize cr_ruidinfo there. o Restruction many credential modification chunks to always crdup while we figure out locking and optimizations; generally speaking, this means moving to a structure like this: newcred = crdup(oldcred); ... p->p_ucred = newcred; crfree(oldcred); It's not race-free, but better than nothing. There are also races in sys_process.c, all inter-process authorization, fork, exec, and exit. o Remove sigio->sio_ruid since sigio->sio_ucred now contains the ruid; remove comments indicating that the old arrangement was a problem. o Restructure exec1() a little to use newcred/oldcred arrangement, and use improved uid management primitives. o Clean up exit1() so as to do less work in credential cleanup due to pcred removal. o Clean up fork1() so as to do less work in credential cleanup and allocation. o Clean up ktrcanset() to take into account changes, and move to using suser_xxx() instead of performing a direct uid==0 comparision. o Improve commenting in various kern_prot.c credential modification calls to better document current behavior. In a couple of places, current behavior is a little questionable and we need to check POSIX.1 to make sure it's "right". More commenting work still remains to be done. o Update credential management calls, such as crfree(), to take into account new ruidinfo reference. o Modify or add the following uid and gid helper routines: change_euid() change_egid() change_ruid() change_rgid() change_svuid() change_svgid() In each case, the call now acts on a credential not a process, and as such no longer requires more complicated process locking/etc. They now assume the caller will do any necessary allocation of an exclusive credential reference. Each is commented to document its reference requirements. o CANSIGIO() is simplified to require only credentials, not processes and pcreds. o Remove lots of (p_pcred==NULL) checks. o Add an XXX to authorization code in nfs_lock.c, since it's questionable, and needs to be considered carefully. o Simplify posix4 authorization code to require only credentials, not processes and pcreds. Note that this authorization, as well as CANSIGIO(), needs to be updated to use the p_cansignal() and p_cansched() centralized authorization routines, as they currently do not take into account some desirable restrictions that are handled by the centralized routines, as well as being inconsistent with other similar authorization instances. o Update libkvm to take these changes into account. Obtained from: TrustedBSD Project Reviewed by: green, bde, jhb, freebsd-arch, freebsd-audit
2001-05-25 16:59:11 +00:00
(void)chgproccnt(p->p_ucred->cr_ruidinfo, 1, 0);
}
SYSINIT(p0init, SI_SUB_INTRINSIC, SI_ORDER_FIRST, proc0_init, NULL)
1994-05-24 10:09:53 +00:00
/* ARGSUSED*/
static void
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
proc0_post(void *dummy __unused)
{
struct timespec ts;
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
struct proc *p;
struct rusage ru;
struct thread *td;
/*
* Now we can look at the time, having had a chance to verify the
2002-05-16 21:28:32 +00:00
* time from the filesystem. Pretend that proc0 started now.
*/
sx_slock(&allproc_lock);
FOREACH_PROC_IN_SYSTEM(p) {
microuptime(&p->p_stats->p_start);
PROC_SLOCK(p);
rufetch(p, &ru); /* Clears thread stats */
PROC_SUNLOCK(p);
p->p_rux.rux_runtime = 0;
p->p_rux.rux_uticks = 0;
p->p_rux.rux_sticks = 0;
p->p_rux.rux_iticks = 0;
FOREACH_THREAD_IN_PROC(p, td) {
td->td_runtime = 0;
}
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
}
sx_sunlock(&allproc_lock);
PCPU_SET(switchtime, cpu_ticks());
PCPU_SET(switchticks, ticks);
/*
* Give the ``random'' number generator a thump.
*/
nanotime(&ts);
srandom(ts.tv_sec ^ ts.tv_nsec);
}
SYSINIT(p0post, SI_SUB_INTRINSIC_POST, SI_ORDER_FIRST, proc0_post, NULL)
1994-05-24 10:09:53 +00:00
/*
***************************************************************************
****
**** The following SYSINIT's and glue code should be moved to the
**** respective files on a per subsystem basis.
****
***************************************************************************
*/
1994-05-24 10:09:53 +00:00
/*
***************************************************************************
****
**** The following code probably belongs in another file, like
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
**** kern/init_init.c.
****
***************************************************************************
*/
1994-05-24 10:09:53 +00:00
/*
* List of paths to try when searching for "init".
*/
static char init_path[MAXPATHLEN] =
#ifdef INIT_PATH
__XSTRING(INIT_PATH);
#else
"/sbin/init:/sbin/oinit:/sbin/init.bak:/rescue/init:/stand/sysinstall";
#endif
SYSCTL_STRING(_kern, OID_AUTO, init_path, CTLFLAG_RD, init_path, 0,
"Path used to search the init process");
1994-05-24 10:09:53 +00:00
/*
* Shutdown timeout of init(8).
* Unused within kernel, but used to control init(8), hence do not remove.
*/
#ifndef INIT_SHUTDOWN_TIMEOUT
#define INIT_SHUTDOWN_TIMEOUT 120
#endif
static int init_shutdown_timeout = INIT_SHUTDOWN_TIMEOUT;
SYSCTL_INT(_kern, OID_AUTO, init_shutdown_timeout,
CTLFLAG_RW, &init_shutdown_timeout, 0, "");
1994-05-24 10:09:53 +00:00
/*
* Start the initial user process; try exec'ing each pathname in init_path.
1994-05-24 10:09:53 +00:00
* The program is invoked with one argument containing the boot flags.
*/
static void
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
start_init(void *dummy)
1994-05-24 10:09:53 +00:00
{
vm_offset_t addr;
struct execve_args args;
int options, error;
char *var, *path, *next, *s;
char *ucp, **uap, *arg0, *arg1;
struct thread *td;
struct proc *p;
1994-05-24 10:09:53 +00:00
Change and clean the mutex lock interface. mtx_enter(lock, type) becomes: mtx_lock(lock) for sleep locks (MTX_DEF-initialized locks) mtx_lock_spin(lock) for spin locks (MTX_SPIN-initialized) similarily, for releasing a lock, we now have: mtx_unlock(lock) for MTX_DEF and mtx_unlock_spin(lock) for MTX_SPIN. We change the caller interface for the two different types of locks because the semantics are entirely different for each case, and this makes it explicitly clear and, at the same time, it rids us of the extra `type' argument. The enter->lock and exit->unlock change has been made with the idea that we're "locking data" and not "entering locked code" in mind. Further, remove all additional "flags" previously passed to the lock acquire/release routines with the exception of two: MTX_QUIET and MTX_NOSWITCH The functionality of these flags is preserved and they can be passed to the lock/unlock routines by calling the corresponding wrappers: mtx_{lock, unlock}_flags(lock, flag(s)) and mtx_{lock, unlock}_spin_flags(lock, flag(s)) for MTX_DEF and MTX_SPIN locks, respectively. Re-inline some lock acq/rel code; in the sleep lock case, we only inline the _obtain_lock()s in order to ensure that the inlined code fits into a cache line. In the spin lock case, we inline recursion and actually only perform a function call if we need to spin. This change has been made with the idea that we generally tend to avoid spin locks and that also the spin locks that we do have and are heavily used (i.e. sched_lock) do recurse, and therefore in an effort to reduce function call overhead for some architectures (such as alpha), we inline recursion for this case. Create a new malloc type for the witness code and retire from using the M_DEV type. The new type is called M_WITNESS and is only declared if WITNESS is enabled. Begin cleaning up some machdep/mutex.h code - specifically updated the "optimized" inlined code in alpha/mutex.h and wrote MTX_LOCK_SPIN and MTX_UNLOCK_SPIN asm macros for the i386/mutex.h as we presently need those. Finally, caught up to the interface changes in all sys code. Contributors: jake, jhb, jasone (in no particular order)
2001-02-09 06:11:45 +00:00
mtx_lock(&Giant);
GIANT_REQUIRED;
td = curthread;
p = td->td_proc;
1994-05-24 10:09:53 +00:00
vfs_mountroot();
1994-05-24 10:09:53 +00:00
/*
* Need just enough stack to hold the faked-up "execve()" arguments.
*/
addr = p->p_sysent->sv_usrstack - 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)
1994-05-24 10:09:53 +00:00
panic("init: couldn't allocate argument space");
p->p_vmspace->vm_maxsaddr = (caddr_t)addr;
p->p_vmspace->vm_ssize = 1;
1994-05-24 10:09:53 +00:00
if ((var = getenv("init_path")) != NULL) {
strlcpy(init_path, var, sizeof(init_path));
freeenv(var);
}
for (path = init_path; *path != '\0'; path = next) {
while (*path == ':')
path++;
if (*path == '\0')
break;
for (next = path; *next != '\0' && *next != ':'; next++)
/* nothing */ ;
if (bootverbose)
1999-04-24 18:50:48 +00:00
printf("start_init: trying %.*s\n", (int)(next - path),
path);
1994-05-24 10:09:53 +00:00
/*
* Move out the boot flag argument.
*/
options = 0;
ucp = (char *)p->p_sysent->sv_usrstack;
1994-05-24 10:09:53 +00:00
(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
1994-05-24 10:09:53 +00:00
if (options == 0)
(void)subyte(--ucp, '-');
(void)subyte(--ucp, '-'); /* leading hyphen */
arg1 = ucp;
/*
* Move out the file name (also arg 0).
*/
(void)subyte(--ucp, 0);
for (s = next - 1; s >= path; s--)
(void)subyte(--ucp, *s);
1994-05-24 10:09:53 +00:00
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);
1994-05-24 10:09:53 +00:00
/*
* Point at the arguments.
*/
args.fname = arg0;
args.argv = uap;
args.envv = NULL;
1994-05-24 10:09:53 +00:00
/*
* Now try to exec the program. If can't for any reason
* other than it doesn't exist, complain.
*
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
* Otherwise, return via fork_trampoline() all the way
* to user mode as init!
1994-05-24 10:09:53 +00:00
*/
if ((error = execve(td, &args)) == 0) {
Change and clean the mutex lock interface. mtx_enter(lock, type) becomes: mtx_lock(lock) for sleep locks (MTX_DEF-initialized locks) mtx_lock_spin(lock) for spin locks (MTX_SPIN-initialized) similarily, for releasing a lock, we now have: mtx_unlock(lock) for MTX_DEF and mtx_unlock_spin(lock) for MTX_SPIN. We change the caller interface for the two different types of locks because the semantics are entirely different for each case, and this makes it explicitly clear and, at the same time, it rids us of the extra `type' argument. The enter->lock and exit->unlock change has been made with the idea that we're "locking data" and not "entering locked code" in mind. Further, remove all additional "flags" previously passed to the lock acquire/release routines with the exception of two: MTX_QUIET and MTX_NOSWITCH The functionality of these flags is preserved and they can be passed to the lock/unlock routines by calling the corresponding wrappers: mtx_{lock, unlock}_flags(lock, flag(s)) and mtx_{lock, unlock}_spin_flags(lock, flag(s)) for MTX_DEF and MTX_SPIN locks, respectively. Re-inline some lock acq/rel code; in the sleep lock case, we only inline the _obtain_lock()s in order to ensure that the inlined code fits into a cache line. In the spin lock case, we inline recursion and actually only perform a function call if we need to spin. This change has been made with the idea that we generally tend to avoid spin locks and that also the spin locks that we do have and are heavily used (i.e. sched_lock) do recurse, and therefore in an effort to reduce function call overhead for some architectures (such as alpha), we inline recursion for this case. Create a new malloc type for the witness code and retire from using the M_DEV type. The new type is called M_WITNESS and is only declared if WITNESS is enabled. Begin cleaning up some machdep/mutex.h code - specifically updated the "optimized" inlined code in alpha/mutex.h and wrote MTX_LOCK_SPIN and MTX_UNLOCK_SPIN asm macros for the i386/mutex.h as we presently need those. Finally, caught up to the interface changes in all sys code. Contributors: jake, jhb, jasone (in no particular order)
2001-02-09 06:11:45 +00:00
mtx_unlock(&Giant);
1994-05-24 10:09:53 +00:00
return;
}
1994-05-24 10:09:53 +00:00
if (error != ENOENT)
1999-04-24 18:50:48 +00:00
printf("exec %.*s: error %d\n", (int)(next - path),
path, error);
1994-05-24 10:09:53 +00:00
}
printf("init: not found in path %s\n", init_path);
1994-05-24 10:09:53 +00:00
panic("no init");
}
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
/*
* Like kproc_create(), but runs in it's own address space.
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
* We do this early to reserve pid 1.
*
* Note special case - do not make it runnable yet. Other work
* in progress will change this more.
*/
static void
create_init(const void *udata __unused)
{
struct ucred *newcred, *oldcred;
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
int error;
error = fork1(&thread0, RFFDG | RFPROC | RFSTOPPED, 0, &initproc);
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
if (error)
panic("cannot fork init: %d\n", error);
KASSERT(initproc->p_pid == 1, ("create_init: initproc->p_pid != 1"));
/* divorce init's credentials from the kernel's */
newcred = crget();
PROC_LOCK(initproc);
initproc->p_flag |= P_SYSTEM | P_INMEM;
oldcred = initproc->p_ucred;
crcopy(newcred, oldcred);
#ifdef MAC
mac_proc_create_init(newcred);
#endif
#ifdef AUDIT
audit_cred_proc1(newcred);
#endif
initproc->p_ucred = newcred;
PROC_UNLOCK(initproc);
crfree(oldcred);
cred_update_thread(FIRST_THREAD_IN_PROC(initproc));
cpu_set_fork_handler(FIRST_THREAD_IN_PROC(initproc), start_init, NULL);
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
}
SYSINIT(init, SI_SUB_CREATE_INIT, SI_ORDER_FIRST, create_init, NULL)
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
/*
* Make it runnable now.
*/
static void
kick_init(const void *udata __unused)
{
struct thread *td;
td = FIRST_THREAD_IN_PROC(initproc);
thread_lock(td);
TD_SET_CAN_RUN(td);
sched_add(td, SRQ_BORING);
thread_unlock(td);
Clean up some low level bootstrap code: - stop using the evil 'struct trapframe' argument for mi_startup() (formerly main()). There are much better ways of doing it. - do not use prepare_usermode() - setregs() in execve() will do it all for us as long as the p_md.md_regs pointer is set. (which is now done in machdep.c rather than init_main.c. The Alpha port did it this way all along and is much cleaner). - collect all the magic %cr0 etc register settings into one place and have the AP's call that instead of using magic numbers (!!) that keep changing over and over again. - Make it safe to call kthread_create() earlier, including during the device probe sequence. It doesn't need the callback mechanism that NetBSD's version uses. - kthreads created this way are root-less as they exist before the root filesystem is mounted. init(1) is set up so that it aquires the root pointers prior to running. If other kthreads want filesystem acccess we can make this code more generic. - set all threads start times once we have decided what time it is. - init uses a trampoline rather than the evil prepare_usermode() hack. - kern_descrip.c has a couple of tweaks to deal with forking when there is no rootdir or cwd etc. - adjust the early SYSINIT() sequence so that a few prereqisites are in place. eg: make sure the run queue is initialized before doing forks. With this, the USB code can easily create a kthread to do the device tree discovery. (I have tested it, it works nicely). There are still some open issues before this is truely useful. - tsleep() does not like working before the clock is running. It sort-of tries to spin wait, but it can do more useful things now. - stopping a kthread in kld code at unload time is "interesting" but we have a solution for that. The Alpha code needs no changes for this. It already uses pretty much the same strategies, but a little cleaner.
2000-08-11 09:05:12 +00:00
}
SYSINIT(kickinit, SI_SUB_KTHREAD_INIT, SI_ORDER_FIRST, kick_init, NULL)