minix/servers/pm/misc.c

624 lines
17 KiB
C
Raw Normal View History

/* Miscellaneous system calls. Author: Kees J. Bot
* 31 Mar 2000
* The entry points into this file are:
* do_reboot: kill all processes, then reboot system
2006-03-10 17:10:05 +01:00
* do_procstat: request process status (Jorrit N. Herder)
* do_getsysinfo: request copy of PM data structure (Jorrit N. Herder)
* do_getprocnr: lookup process slot number (Jorrit N. Herder)
2009-10-31 15:09:28 +01:00
* do_getepinfo: get the pid/uid/gid of a process given its endpoint
* do_getsetpriority: get/set process priority
2006-03-10 17:10:05 +01:00
* do_svrctl: process manager control
*/
#define brk _brk
#include "pm.h"
#include <minix/callnr.h>
#include <signal.h>
#include <sys/svrctl.h>
#include <sys/resource.h>
#include <sys/utsname.h>
#include <minix/com.h>
#include <minix/config.h>
#include <minix/sysinfo.h>
#include <minix/type.h>
#include <minix/vm.h>
#include <string.h>
#include <machine/archtypes.h>
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
#include <lib.h>
#include <assert.h>
#include "mproc.h"
#include "param.h"
2010-04-02 00:22:33 +02:00
#include "kernel/proc.h"
PUBLIC struct utsname uts_val = {
"Minix", /* system name */
"noname", /* node/network name */
OS_RELEASE, /* O.S. release (e.g. 1.5) */
OS_VERSION, /* O.S. version (e.g. 10) */
"xyzzy", /* machine (cpu) type (filled in later) */
#if __i386
"i386", /* architecture */
#else
#error /* oops, no 'uname -mk' */
#endif
};
PRIVATE char *uts_tbl[] = {
uts_val.arch,
NULL, /* No kernel architecture */
uts_val.machine,
NULL, /* No hostname */
uts_val.nodename,
uts_val.release,
uts_val.version,
uts_val.sysname,
NULL, /* No bus */ /* No bus */
};
#if ENABLE_SYSCALL_STATS
PUBLIC unsigned long calls_stats[NCALLS];
#endif
FORWARD _PROTOTYPE( int getpciinfo, (struct pciinfo *pciinfo) );
2006-03-10 17:10:05 +01:00
/*===========================================================================*
* do_procstat *
*===========================================================================*/
PUBLIC int do_procstat()
{
/* For the moment, this is only used to return pending signals to
* system processes that request the PM for their own status.
*
* Future use might include the VFS requesting for process status of
2006-03-10 17:10:05 +01:00
* any user process.
*/
/* This call should be removed, or made more general. */
2006-03-10 17:10:05 +01:00
if (m_in.stat_nr == SELF) {
mp->mp_reply.sig_set = mp->mp_sigpending;
sigemptyset(&mp->mp_sigpending);
}
else {
return(ENOSYS);
}
return(OK);
}
/*===========================================================================*
* do_sysuname *
*===========================================================================*/
PUBLIC int do_sysuname()
{
/* Set or get uname strings. */
int r;
size_t n;
char *string;
#if 0 /* for updates */
char tmp[sizeof(uts_val.nodename)];
static short sizes[] = {
0, /* arch, (0 = read-only) */
0, /* kernel */
0, /* machine */
0, /* sizeof(uts_val.hostname), */
sizeof(uts_val.nodename),
0, /* release */
0, /* version */
0, /* sysname */
};
#endif
if ((unsigned) m_in.sysuname_field >= _UTS_MAX) return(EINVAL);
string = uts_tbl[m_in.sysuname_field];
if (string == NULL)
return EINVAL; /* Unsupported field */
switch (m_in.sysuname_req) {
case _UTS_GET:
/* Copy an uname string to the user. */
n = strlen(string) + 1;
if (n > m_in.sysuname_len) n = m_in.sysuname_len;
r = sys_vircopy(SELF, D, (phys_bytes) string,
mp->mp_endpoint, D, (phys_bytes) m_in.sysuname_value,
(phys_bytes) n);
if (r < 0) return(r);
break;
#if 0 /* no updates yet */
case _UTS_SET:
/* Set an uname string, needs root power. */
len = sizes[m_in.sysuname_field];
if (mp->mp_effuid != 0 || len == 0) return(EPERM);
n = len < m_in.sysuname_len ? len : m_in.sysuname_len;
if (n <= 0) return(EINVAL);
r = sys_vircopy(mp->mp_endpoint, D, (phys_bytes) m_in.sysuname_value,
SELF, D, (phys_bytes) tmp, (phys_bytes) n);
if (r < 0) return(r);
tmp[n-1] = 0;
strcpy(string, tmp);
break;
#endif
default:
return(EINVAL);
}
/* Return the number of bytes moved. */
return(n);
}
/*===========================================================================*
2005-09-11 18:45:46 +02:00
* do_getsysinfo *
*===========================================================================*/
PUBLIC int do_getsysinfo()
{
struct mproc *proc_addr;
vir_bytes src_addr, dst_addr;
struct kinfo kinfo;
struct loadinfo loadinfo;
struct pciinfo pciinfo;
static struct proc proctab[NR_PROCS+NR_TASKS];
size_t len;
int s, r;
2009-09-12 20:36:07 +02:00
/* This call leaks important information (the contents of registers). */
if (mp->mp_effuid != 0)
{
printf("PM: unauthorized call of do_getsysinfo by proc %d '%s'\n",
mp->mp_endpoint, mp->mp_name);
sys_sysctl_stacktrace(mp->mp_endpoint);
return EPERM;
}
switch(m_in.info_what) {
case SI_KINFO: /* kernel info is obtained via PM */
sys_getkinfo(&kinfo);
src_addr = (vir_bytes) &kinfo;
len = sizeof(struct kinfo);
break;
case SI_PROC_ADDR: /* get address of PM process table */
proc_addr = &mproc[0];
src_addr = (vir_bytes) &proc_addr;
len = sizeof(struct mproc *);
break;
case SI_PROC_TAB: /* copy entire process table */
src_addr = (vir_bytes) mproc;
len = sizeof(struct mproc) * NR_PROCS;
break;
case SI_KPROC_TAB: /* copy entire process table */
if((r=sys_getproctab(proctab)) != OK)
return r;
src_addr = (vir_bytes) proctab;
len = sizeof(proctab);
break;
case SI_LOADINFO: /* loadinfo is obtained via PM */
sys_getloadinfo(&loadinfo);
src_addr = (vir_bytes) &loadinfo;
len = sizeof(struct loadinfo);
break;
case SI_PCI_INFO: /* PCI info is obtained via PM */
if ((r=getpciinfo(&pciinfo)) != OK)
return r;
src_addr = (vir_bytes) &pciinfo;
len = sizeof(struct pciinfo);
break;
#if ENABLE_SYSCALL_STATS
case SI_CALL_STATS:
src_addr = (vir_bytes) calls_stats;
len = sizeof(calls_stats);
break;
#endif
default:
return(EINVAL);
}
dst_addr = (vir_bytes) m_in.info_where;
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
if (OK != (s=sys_datacopy(SELF, src_addr, who_e, dst_addr, len)))
return(s);
return(OK);
}
/*===========================================================================*
* do_getsysinfo_up *
*===========================================================================*/
PUBLIC int do_getsysinfo_up()
{
vir_bytes src_addr, dst_addr;
struct loadinfo loadinfo;
size_t len, real_len;
u64_t idle_tsc;
int s;
switch(m_in.SIU_WHAT) {
case SIU_LOADINFO: /* loadinfo is obtained via PM */
if ((s = sys_getloadinfo(&loadinfo)) != OK)
return s;
src_addr = (vir_bytes) &loadinfo;
real_len = sizeof(struct loadinfo);
break;
case SIU_SYSTEMHZ:
src_addr = (vir_bytes) &system_hz;
real_len = sizeof(system_hz);
break;
case SIU_IDLETSC:
if ((s = sys_getidletsc(&idle_tsc)) != OK)
return s;
src_addr = (vir_bytes) &idle_tsc;
real_len = sizeof(idle_tsc);
break;
default:
return(EINVAL);
}
/* Let application know what the length was. */
len = real_len;
if(len > m_in.SIU_LEN)
len = m_in.SIU_LEN;
dst_addr = (vir_bytes) m_in.SIU_WHERE;
if (OK != (s=sys_datacopy(SELF, src_addr, who_e, dst_addr, len)))
return(s);
return(real_len);
}
/*===========================================================================*
2005-09-11 18:45:46 +02:00
* do_getprocnr *
*===========================================================================*/
2005-05-19 11:38:29 +02:00
PUBLIC int do_getprocnr()
{
register struct mproc *rmp;
static char search_key[PROC_NAME_LEN+1];
int key_len;
int s;
/* This call should be moved to DS. */
if (mp->mp_effuid != 0)
{
/* For now, allow non-root processes to request their own endpoint. */
if (m_in.pid < 0 && m_in.namelen == 0) {
mp->mp_reply.PM_ENDPT = who_e;
mp->mp_reply.PM_PENDPT = NONE;
return OK;
}
printf("PM: unauthorized call of do_getprocnr by proc %d\n",
mp->mp_endpoint);
sys_sysctl_stacktrace(mp->mp_endpoint);
return EPERM;
}
#if 0
printf("PM: do_getprocnr(%d) call from endpoint %d, %s\n",
m_in.pid, mp->mp_endpoint, mp->mp_name);
#endif
if (m_in.pid >= 0) { /* lookup process by pid */
if ((rmp = find_proc(m_in.pid)) != NULL) {
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
mp->mp_reply.PM_ENDPT = rmp->mp_endpoint;
#if 0
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
printf("PM: pid result: %d\n", rmp->mp_endpoint);
#endif
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
return(OK);
}
return(ESRCH);
} else if (m_in.namelen > 0) { /* lookup process by name */
key_len = MIN(m_in.namelen, PROC_NAME_LEN);
if (OK != (s=sys_datacopy(who_e, (vir_bytes) m_in.PMBRK_ADDR,
SELF, (vir_bytes) search_key, key_len)))
return(s);
search_key[key_len] = '\0'; /* terminate for safety */
for (rmp = &mproc[0]; rmp < &mproc[NR_PROCS]; rmp++) {
if (((rmp->mp_flags & (IN_USE | EXITING)) == IN_USE) &&
strncmp(rmp->mp_name, search_key, key_len)==0) {
mp->mp_reply.PM_ENDPT = rmp->mp_endpoint;
return(OK);
}
}
return(ESRCH);
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
} else { /* return own/parent process number */
#if 0
printf("PM: endpt result: %d\n", mp->mp_reply.PM_ENDPT);
#endif
mp->mp_reply.PM_ENDPT = who_e;
mp->mp_reply.PM_PENDPT = mproc[mp->mp_parent].mp_endpoint;
}
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
2005-05-19 11:38:29 +02:00
return(OK);
}
/*===========================================================================*
2009-10-31 15:09:28 +01:00
* do_getepinfo *
*===========================================================================*/
2009-10-31 15:09:28 +01:00
PUBLIC int do_getepinfo()
{
register struct mproc *rmp;
endpoint_t ep;
/* This call should be moved to DS. */
if (mp->mp_effuid != 0)
{
2009-10-31 15:09:28 +01:00
printf("PM: unauthorized call of do_getepinfo by proc %d\n",
mp->mp_endpoint);
sys_sysctl_stacktrace(mp->mp_endpoint);
return EPERM;
}
ep= m_in.PM_ENDPT;
for (rmp = &mproc[0]; rmp < &mproc[NR_PROCS]; rmp++) {
if ((rmp->mp_flags & IN_USE) && (rmp->mp_endpoint == ep)) {
mp->mp_reply.reply_res2 = rmp->mp_effuid;
2009-10-31 15:09:28 +01:00
mp->mp_reply.reply_res3 = rmp->mp_effgid;
return(rmp->mp_pid);
}
}
/* Process not found */
2009-10-31 15:09:28 +01:00
return(ESRCH);
}
2005-09-11 18:45:46 +02:00
/*===========================================================================*
* do_reboot *
*===========================================================================*/
PUBLIC int do_reboot()
{
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
message m;
2006-03-10 17:10:05 +01:00
/* Check permission to abort the system. */
if (mp->mp_effuid != SUPER_USER) return(EPERM);
2006-03-10 17:10:05 +01:00
/* See how the system should be aborted. */
abort_flag = (unsigned) m_in.reboot_flag;
if (abort_flag >= RBT_INVALID) return(EINVAL);
2006-03-13 11:36:52 +01:00
if (RBT_MONITOR == abort_flag) {
int r;
if(m_in.reboot_strlen >= sizeof(monitor_code))
return EINVAL;
if((r = sys_datacopy(who_e, (vir_bytes) m_in.reboot_code,
SELF, (vir_bytes) monitor_code, m_in.reboot_strlen)) != OK)
return r;
monitor_code[m_in.reboot_strlen] = '\0';
}
2006-05-11 16:57:23 +02:00
else
monitor_code[0] = '\0';
/* Order matters here. When VFS is told to reboot, it exits all its
* processes, and then would be confused if they're exited again by
2006-03-10 17:10:05 +01:00
* SIGKILL. So first kill, then reboot.
*/
check_sig(-1, SIGKILL, FALSE /* ksig*/); /* kill all users except init */
sys_stop(INIT_PROC_NR); /* stop init, but keep it around */
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
2010-06-09 16:31:30 +02:00
/* Tell VFS to reboot */
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
m.m_type = PM_REBOOT;
2010-06-09 16:31:30 +02:00
tell_vfs(&mproc[VFS_PROC_NR], &m);
2006-03-10 17:10:05 +01:00
return(SUSPEND); /* don't reply to caller */
}
2005-09-11 18:45:46 +02:00
/*===========================================================================*
* do_getsetpriority *
*===========================================================================*/
PUBLIC int do_getsetpriority()
{
int r, arg_which, arg_who, arg_pri;
struct mproc *rmp;
arg_which = m_in.m1_i1;
arg_who = m_in.m1_i2;
arg_pri = m_in.m1_i3; /* for SETPRIORITY */
/* Code common to GETPRIORITY and SETPRIORITY. */
/* Only support PRIO_PROCESS for now. */
2005-09-11 18:45:46 +02:00
if (arg_which != PRIO_PROCESS)
return(EINVAL);
2005-09-11 18:45:46 +02:00
if (arg_who == 0)
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
rmp = mp;
else
if ((rmp = find_proc(arg_who)) == NULL)
return(ESRCH);
2005-09-11 18:45:46 +02:00
if (mp->mp_effuid != SUPER_USER &&
mp->mp_effuid != rmp->mp_effuid && mp->mp_effuid != rmp->mp_realuid)
return EPERM;
/* If GET, that's it. */
2005-09-11 18:45:46 +02:00
if (call_nr == GETPRIORITY) {
return(rmp->mp_nice - PRIO_MIN);
}
/* Only root is allowed to reduce the nice level. */
2005-09-11 18:45:46 +02:00
if (rmp->mp_nice > arg_pri && mp->mp_effuid != SUPER_USER)
return(EACCES);
Userspace scheduling - cotributed by Bjorn Swift - In this first phase, scheduling is moved from the kernel to the PM server. The next steps are to a) moving scheduling to its own server and b) include useful information in the "out of quantum" message, so that the scheduler can make use of this information. - The kernel process table now keeps record of who is responsible for scheduling each process (p_scheduler). When this pointer is NULL, the process will be scheduled by the kernel. If such a process runs out of quantum, the kernel will simply renew its quantum an requeue it. - When PM loads, it will take over scheduling of all running processes, except system processes, using sys_schedctl(). Essentially, this only results in taking over init. As children inherit a scheduler from their parent, user space programs forked by init will inherit PM (for now) as their scheduler. - Once a process has been assigned a scheduler, and runs out of quantum, its RTS_NO_QUANTUM flag will be set and the process dequeued. The kernel will send a message to the scheduler, on the process' behalf, informing the scheduler that it has run out of quantum. The scheduler can take what ever action it pleases, based on its policy, and then reschedule the process using the sys_schedule() system call. - Balance queues does not work as before. While the old in-kernel function used to renew the quantum of processes in the highest priority run queue, the user-space implementation only acts on processes that have been bumped down to a lower priority queue. This approach reacts slower to changes than the old one, but saves us sending a sys_schedule message for each process every time we balance the queues. Currently, when processes are moved up a priority queue, their quantum is also renewed, but this can be fiddled with. - do_nice has been removed from kernel. PM answers to get- and setpriority calls, updates it's own nice variable as well as the max_run_queue. This will be refactored once scheduling is moved to a separate server. We will probably have PM update it's local nice value and then send a message to whoever is scheduling the process. - changes to fix an issue in do_fork() where processes could run out of quantum but bypassing the code path that handles it correctly. The future plan is to remove the policy from do_fork() and implement it in userspace too.
2010-03-29 13:07:20 +02:00
/* We're SET, and it's allowed.
*
* The value passed in is currently between PRIO_MIN and PRIO_MAX.
* We have to scale this between MIN_USER_Q and MAX_USER_Q to match
* the kernel's scheduling queues.
*/
Scheduling server (by Bjorn Swift) In this second phase, scheduling is moved from PM to its own scheduler (see r6557 for phase one). In the next phase we hope to a) include useful information in the "out of quantum" message and b) create some simple scheduling policy that makes use of that information. When the system starts up, PM will iterate over its process table and ask SCHED to take over scheduling unprivileged processes. This is done by sending a SCHEDULING_START message to SCHED. This message includes the processes endpoint, the parent's endpoint and its nice level. The scheduler adds this process to its schedproc table, issues a schedctl, and returns its own endpoint to PM - as the endpoint of the effective scheduler. When a process terminates, a SCHEDULING_STOP message is sent to the scheduler. The reason for this effective endpoint is for future compatibility. Some day, we may have a scheduler that, instead of scheduling the process itself, forwards the SCHEDULING_START message on to another scheduler. PM has information on who schedules whom. As such, scheduling messages from user-land are sent through PM. An example is when processes change their priority, using nice(). In that case, a getsetpriority message is sent to PM, which then sends a SCHEDULING_SET_NICE to the process's effective scheduler. When a process is forked through PM, it inherits its parent's scheduler, but is spawned with an empty quantum. As before, a request to fork a process flows through VM before returning to PM, which then wakes up the child process. This flow has been modified slightly so that PM notifies the scheduler of the new process, before waking up the child process. If the scheduler fails to take over scheduling, the child process is torn down and the fork fails with an erroneous value. Process priority is entirely decided upon using nice levels. PM stores a copy of each process's nice level and when a child is forked, its parent's nice level is sent in the SCHEDULING_START message. How this level is mapped to a priority queue is up to the scheduler. It should be noted that the nice level is used to determine the max_priority and the parent could have been in a lower priority when it was spawned. To prevent a CPU intensive process from hawking the CPU by continuously forking children that get scheduled in the max_priority, the scheduler should determine in which queue the parent is currently scheduled, and schedule the child in that same queue. Other fixes: The USER_Q in kernel/proc.h was incorrectly defined as NR_SCHED_QUEUES/2. That results in a "off by one" error when converting priority->nice->priority for nice=0. This also had the side effect that if someone were to set the MAX_USER_Q to something else than 0, then USER_Q would be off.
2010-05-18 15:39:04 +02:00
if ((r = sched_nice(rmp, arg_pri)) != OK) {
return r;
}
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
rmp->mp_nice = arg_pri;
Merge of David's ptrace branch. Summary: o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL o PM signal handling logic should now work properly, even with debuggers being present o Asynchronous PM/VFS protocol, full IPC support for senda(), and AMF_NOREPLY senda() flag DETAILS Process stop and delay call handling of PM: o Added sys_runctl() kernel call with sys_stop() and sys_resume() aliases, for PM to stop and resume a process o Added exception for sending/syscall-traced processes to sys_runctl(), and matching SIGKREADY pseudo-signal to PM o Fixed PM signal logic to deal with requests from a process after stopping it (so-called "delay calls"), using the SIGKREADY facility o Fixed various PM panics due to race conditions with delay calls versus VFS calls o Removed special PRIO_STOP priority value o Added SYS_LOCK RTS kernel flag, to stop an individual process from running while modifying its process structure Signal and debugger handling in PM: o Fixed debugger signals being dropped if a second signal arrives when the debugger has not retrieved the first one o Fixed debugger signals being sent to the debugger more than once o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR protocol message o Detached debugger signals from general signal logic and from being blocked on VFS calls, meaning that even VFS can now be traced o Fixed debugger being unable to receive more than one pending signal in one process stop o Fixed signal delivery being delayed needlessly when multiple signals are pending o Fixed wait test for tracer, which was returning for children that were not waited for o Removed second parallel pending call from PM to VFS for any process o Fixed process becoming runnable between exec() and debugger trap o Added support for notifying the debugger before the parent when a debugged child exits o Fixed debugger death causing child to remain stopped forever o Fixed consistently incorrect use of _NSIG Extensions to ptrace(): o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a debugger to and from a process o Added T_SYSCALL ptrace request, to trace system calls o Added T_SETOPT ptrace request, to set trace options o Added TO_TRACEFORK trace option, to attach automatically to children of a traced process o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon a successful exec() of the tracee o Extended T_GETUSER ptrace support to allow retrieving a process's priv structure o Removed T_STOP ptrace request again, as it does not help implementing debuggers properly o Added MINIX3-specific ptrace test (test42) o Added proper manual page for ptrace(2) Asynchronous PM/VFS interface: o Fixed asynchronous messages not being checked when receive() is called with an endpoint other than ANY o Added AMF_NOREPLY senda() flag, preventing such messages from satisfying the receive part of a sendrec() o Added asynsend3() that takes optional flags; asynsend() is now a #define passing in 0 as third parameter o Made PM/VFS protocol asynchronous; reintroduced tell_fs() o Made PM_BASE request/reply number range unique o Hacked in a horrible temporary workaround into RS to deal with newly revealed RS-PM-VFS race condition triangle until VFS is asynchronous System signal handling: o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal o Removed is-superuser check from PM's do_procstat() (aka getsigset()) o Added sigset macros to allow system processes to deal with the full signal set, rather than just the POSIX subset Miscellaneous PM fixes: o Split do_getset into do_get and do_set, merging common code and making structure clearer o Fixed setpriority() being able to put to sleep processes using an invalid parameter, or revive zombie processes o Made find_proc() global; removed obsolete proc_from_pid() o Cleanup here and there Also included: o Fixed false-positive boot order kernel warning o Removed last traces of old NOTIFY_FROM code THINGS OF POSSIBLE INTEREST o It should now be possible to run PM at any priority, even lower than user processes o No assumptions are made about communication speed between PM and VFS, although communication must be FIFO o A debugger will now receive incoming debuggee signals at kill time only; the process may not yet be fully stopped o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 11:57:22 +02:00
return(OK);
}
2005-09-11 18:45:46 +02:00
/*===========================================================================*
* do_svrctl *
*===========================================================================*/
PUBLIC int do_svrctl()
{
int s, req;
vir_bytes ptr;
#define MAX_LOCAL_PARAMS 2
static struct {
char name[30];
char value[30];
} local_param_overrides[MAX_LOCAL_PARAMS];
static int local_params = 0;
req = m_in.svrctl_req;
ptr = (vir_bytes) m_in.svrctl_argp;
/* Is the request indeed for the PM? */
if (((req >> 8) & 0xFF) != 'M') return(EINVAL);
/* Control operations local to the PM. */
switch(req) {
case PMSETPARAM:
case PMGETPARAM: {
struct sysgetenv sysgetenv;
char search_key[64];
char *val_start;
size_t val_len;
size_t copy_len;
/* Copy sysgetenv structure to PM. */
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
if (sys_datacopy(who_e, ptr, SELF, (vir_bytes) &sysgetenv,
sizeof(sysgetenv)) != OK) return(EFAULT);
/* Set a param override? */
if (req == PMSETPARAM) {
2005-09-11 18:45:46 +02:00
if (local_params >= MAX_LOCAL_PARAMS) return ENOSPC;
if (sysgetenv.keylen <= 0
2005-08-29 18:47:18 +02:00
|| sysgetenv.keylen >=
sizeof(local_param_overrides[local_params].name)
|| sysgetenv.vallen <= 0
|| sysgetenv.vallen >=
sizeof(local_param_overrides[local_params].value))
return EINVAL;
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
if ((s = sys_datacopy(who_e, (vir_bytes) sysgetenv.key,
2005-08-29 18:47:18 +02:00
SELF, (vir_bytes) local_param_overrides[local_params].name,
sysgetenv.keylen)) != OK)
return s;
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
if ((s = sys_datacopy(who_e, (vir_bytes) sysgetenv.val,
2005-08-29 18:47:18 +02:00
SELF, (vir_bytes) local_param_overrides[local_params].value,
sysgetenv.vallen)) != OK)
2005-08-29 18:47:18 +02:00
return s;
local_param_overrides[local_params].name[sysgetenv.keylen] = '\0';
local_param_overrides[local_params].value[sysgetenv.vallen] = '\0';
local_params++;
return OK;
}
if (sysgetenv.keylen == 0) { /* copy all parameters */
val_start = monitor_params;
val_len = sizeof(monitor_params);
}
else { /* lookup value for key */
int p;
/* Try to get a copy of the requested key. */
if (sysgetenv.keylen > sizeof(search_key)) return(EINVAL);
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
if ((s = sys_datacopy(who_e, (vir_bytes) sysgetenv.key,
SELF, (vir_bytes) search_key, sysgetenv.keylen)) != OK)
return(s);
/* Make sure key is null-terminated and lookup value.
* First check local overrides.
*/
search_key[sysgetenv.keylen-1]= '\0';
for(p = 0; p < local_params; p++) {
2005-09-11 18:45:46 +02:00
if (!strcmp(search_key, local_param_overrides[p].name)) {
val_start = local_param_overrides[p].value;
break;
}
}
2005-09-11 18:45:46 +02:00
if (p >= local_params && (val_start = find_param(search_key)) == NULL)
return(ESRCH);
val_len = strlen(val_start) + 1;
}
/* See if it fits in the client's buffer. */
if (val_len > sysgetenv.vallen)
return E2BIG;
/* Value found, make the actual copy (as far as possible). */
copy_len = MIN(val_len, sysgetenv.vallen);
if ((s=sys_datacopy(SELF, (vir_bytes) val_start,
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
who_e, (vir_bytes) sysgetenv.val, copy_len)) != OK)
return(s);
return OK;
}
default:
return(EINVAL);
}
}
/*===========================================================================*
* _brk *
*===========================================================================*/
extern char *_brksize;
PUBLIC int brk(brk_addr)
char *brk_addr;
{
int r;
/* PM wants to call brk() itself. */
if((r=vm_brk(PM_PROC_NR, brk_addr)) != OK) {
#if 0
printf("PM: own brk(%p) failed: vm_brk() returned %d\n",
brk_addr, r);
#endif
return -1;
}
_brksize = brk_addr;
return 0;
}
/*===========================================================================*
* getpciinfo *
*===========================================================================*/
PRIVATE int getpciinfo(pciinfo)
struct pciinfo *pciinfo;
{
int devind, r;
struct pciinfo_entry *entry;
char *name;
u16_t vid, did;
/* look up PCI process number */
pci_init();
/* start enumerating devices */
entry = pciinfo->pi_entries;
r = pci_first_dev(&devind, &vid, &did);
while (r)
{
/* fetch device name */
name = pci_dev_name(vid, did);
if (!name)
name = "";
/* store device information in table */
assert((char *) entry < (char *) (pciinfo + 1));
entry->pie_vid = vid;
entry->pie_did = did;
strncpy(entry->pie_name, name, sizeof(entry->pie_name));
entry->pie_name[sizeof(entry->pie_name) - 1] = 0;
entry++;
/* continue with the next device */
r = pci_next_dev(&devind, &vid, &did);
}
/* store number of entries */
pciinfo->pi_count = entry - pciinfo->pi_entries;
return OK;
}