freebsd-dev/sys/fs/procfs/procfs_status.c

266 lines
7.1 KiB
C
Raw Normal View History

1994-05-24 10:09:53 +00:00
/*
* Copyright (c) 1993 Jan-Simon Pendry
* Copyright (c) 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Jan-Simon Pendry.
*
* 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.
*
* @(#)procfs_status.c 8.4 (Berkeley) 6/15/94
1994-05-24 10:09:53 +00:00
*
* From:
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/exec.h>
#include <sys/jail.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
1994-05-24 10:09:53 +00:00
#include <sys/proc.h>
#include <sys/resourcevar.h>
#include <sys/tty.h>
#include <sys/vnode.h>
1994-05-24 10:09:53 +00:00
#include <vm/vm.h>
#include <vm/pmap.h>
#include <vm/vm_param.h>
#include <fs/procfs/procfs.h>
2000-11-08 21:53:05 +00:00
#define DOCHECK() do { if (ps >= psbuf+sizeof(psbuf)) goto bailout; } while (0)
1994-05-24 10:09:53 +00:00
int
procfs_dostatus(curp, p, pfs, uio)
struct proc *curp;
struct proc *p;
struct pfsnode *pfs;
struct uio *uio;
{
struct session *sess;
struct tty *tp;
struct ucred *cr;
char *ps;
char *sep;
int pid, ppid, pgid, sid;
int i;
int xlen;
int error;
2000-11-08 21:53:05 +00:00
char psbuf[256]; /* XXX - conservative */
1994-05-24 10:09:53 +00:00
if (uio->uio_rw != UIO_READ)
return (EOPNOTSUPP);
pid = p->p_pid;
PROC_LOCK(p);
ppid = p->p_pptr ? p->p_pptr->p_pid : 0;
PROC_UNLOCK(p);
1994-05-24 10:09:53 +00:00
pgid = p->p_pgrp->pg_id;
sess = p->p_pgrp->pg_session;
sid = sess->s_leader ? sess->s_leader->p_pid : 0;
1996-02-02 05:19:20 +00:00
/* comm pid ppid pgid sid maj,min ctty,sldr start ut st wmsg
euid ruid rgid,egid,groups[1 .. NGROUPS]
*/
2000-11-08 21:53:05 +00:00
KASSERT(sizeof(psbuf) > MAXCOMLEN,
("Too short buffer for new MAXCOMLEN"));
1994-05-24 10:09:53 +00:00
ps = psbuf;
bcopy(p->p_comm, ps, MAXCOMLEN);
ps[MAXCOMLEN] = '\0';
ps += strlen(ps);
2000-11-08 21:53:05 +00:00
DOCHECK();
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
" %d %d %d %d ", pid, ppid, pgid, sid);
DOCHECK();
1994-05-24 10:09:53 +00:00
if ((p->p_flag&P_CONTROLT) && (tp = sess->s_ttyp))
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
"%d,%d ", major(tp->t_dev), minor(tp->t_dev));
1994-05-24 10:09:53 +00:00
else
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
"%d,%d ", -1, -1);
DOCHECK();
1994-05-24 10:09:53 +00:00
sep = "";
if (sess->s_ttyvp) {
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, "%sctty", sep);
1994-05-24 10:09:53 +00:00
sep = ",";
2000-11-08 21:53:05 +00:00
DOCHECK();
1994-05-24 10:09:53 +00:00
}
if (SESS_LEADER(p)) {
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, "%ssldr", sep);
1994-05-24 10:09:53 +00:00
sep = ",";
2000-11-08 21:53:05 +00:00
DOCHECK();
}
if (*sep != ',') {
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, "noflags");
DOCHECK();
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_spin(&sched_lock);
2001-01-24 11:20:05 +00:00
if (p->p_sflag & PS_INMEM) {
1994-05-24 10:09:53 +00:00
struct timeval ut, st;
calcru(p, &ut, &st, (struct timeval *) NULL);
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_spin(&sched_lock);
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
" %ld,%ld %ld,%ld %ld,%ld",
p->p_stats->p_start.tv_sec,
p->p_stats->p_start.tv_usec,
ut.tv_sec, ut.tv_usec,
st.tv_sec, st.tv_usec);
2001-01-24 11:20:05 +00:00
} else {
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_spin(&sched_lock);
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
" -1,-1 -1,-1 -1,-1");
2001-01-24 11:20:05 +00:00
}
2000-11-08 21:53:05 +00:00
DOCHECK();
1994-05-24 10:09:53 +00:00
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, " %s",
1994-05-24 10:09:53 +00:00
(p->p_wchan && p->p_wmesg) ? p->p_wmesg : "nochan");
2000-11-08 21:53:05 +00:00
DOCHECK();
1994-05-24 10:09:53 +00:00
cr = p->p_ucred;
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, " %lu %lu %lu",
1998-07-11 07:46:16 +00:00
(u_long)cr->cr_uid,
(u_long)p->p_cred->p_ruid,
(u_long)p->p_cred->p_rgid);
2000-11-08 21:53:05 +00:00
DOCHECK();
1996-02-02 05:19:20 +00:00
/* egid (p->p_cred->p_svgid) is equal to cr_ngroups[0]
see also getegid(2) in /sys/kern/kern_prot.c */
2000-11-08 21:53:05 +00:00
for (i = 0; i < cr->cr_ngroups; i++) {
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
",%lu", (u_long)cr->cr_groups[i]);
DOCHECK();
}
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
if (jailed(p->p_ucred))
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps,
" %s", p->p_ucred->cr_prison->pr_host);
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
else
2000-11-08 21:53:05 +00:00
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, " -");
DOCHECK();
ps += snprintf(ps, psbuf + sizeof(psbuf) - ps, "\n");
DOCHECK();
1994-05-24 10:09:53 +00:00
xlen = ps - psbuf;
xlen -= uio->uio_offset;
ps = psbuf + uio->uio_offset;
xlen = imin(xlen, uio->uio_resid);
1994-05-24 10:09:53 +00:00
if (xlen <= 0)
error = 0;
else
error = uiomove(ps, xlen, uio);
return (error);
2000-11-08 21:53:05 +00:00
bailout:
return (ENOMEM);
1994-05-24 10:09:53 +00:00
}
int
procfs_docmdline(curp, p, pfs, uio)
struct proc *curp;
struct proc *p;
struct pfsnode *pfs;
struct uio *uio;
{
char *ps;
int xlen;
int error;
char *buf, *bp;
int buflen;
struct ps_strings pstr;
int i;
size_t bytes_left, done;
if (uio->uio_rw != UIO_READ)
return (EOPNOTSUPP);
/*
* If we are using the ps/cmdline caching, use that. Otherwise
* revert back to the old way which only implements full cmdline
* for the currept process and just p->p_comm for all other
* processes.
* Note that if the argv is no longer available, we deliberately
* don't fall back on p->p_comm or return an error: the authentic
* Linux behaviour is to return zero-length in this case.
*/
o Centralize inter-process access control, introducing: int p_can(p1, p2, operation, privused) which allows specification of subject process, object process, inter-process operation, and an optional call-by-reference privused flag, allowing the caller to determine if privilege was required for the call to succeed. This allows jail, kern.ps_showallprocs and regular credential-based interaction checks to occur in one block of code. Possible operations are P_CAN_SEE, P_CAN_SCHED, P_CAN_KILL, and P_CAN_DEBUG. p_can currently breaks out as a wrapper to a series of static function checks in kern_prot, which should not be invoked directly. o Commented out capabilities entries are included for some checks. o Update most inter-process authorization to make use of p_can() instead of manual checks, PRISON_CHECK(), P_TRESPASS(), and kern.ps_showallprocs. o Modify suser{,_xxx} to use const arguments, as it no longer modifies process flags due to the disabling of ASU. o Modify some checks/errors in procfs so that ENOENT is returned instead of ESRCH, further improving concealment of processes that should not be visible to other processes. Also introduce new access checks to improve hiding of processes for procfs_lookup(), procfs_getattr(), procfs_readdir(). Correct a bug reported by bp concerning not handling the CREATE case in procfs_lookup(). Remove volatile flag in procfs that caused apparently spurious qualifier warnigns (approved by bde). o Add comment noting that ktrace() has not been updated, as its access control checks are different from ptrace(), whereas they should probably be the same. Further discussion should happen on this topic. Reviewed by: bde, green, phk, freebsd-security, others Approved by: bde Obtained from: TrustedBSD Project
2000-08-30 04:49:09 +00:00
if (p->p_args && (ps_argsopen || !p_can(curp, p, P_CAN_SEE, NULL))) {
bp = p->p_args->ar_args;
buflen = p->p_args->ar_length;
buf = 0;
} else if (p != curp) {
bp = p->p_comm;
buflen = MAXCOMLEN;
buf = 0;
} else {
buflen = 256;
MALLOC(buf, char *, buflen + 1, M_TEMP, M_WAITOK);
bp = buf;
ps = buf;
error = copyin((void*)PS_STRINGS, &pstr, sizeof(pstr));
if (error) {
FREE(buf, M_TEMP);
return (error);
}
bytes_left = buflen;
for (i = 0; bytes_left && (i < pstr.ps_nargvstr); i++) {
error = copyinstr(pstr.ps_argvstr[i], ps,
bytes_left, &done);
/* If too long or malformed, just truncate */
if (error) {
error = 0;
break;
}
ps += done;
bytes_left -= done;
}
buflen = ps - buf;
}
buflen -= uio->uio_offset;
ps = bp + uio->uio_offset;
xlen = min(buflen, uio->uio_resid);
if (xlen <= 0)
error = 0;
else
error = uiomove(ps, xlen, uio);
if (buf)
FREE(buf, M_TEMP);
return (error);
}