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

222 lines
5.9 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.
* 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:
* $Id: procfs_status.c,v 3.1 1993/12/15 09:40:17 jsp Exp $
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
#include <sys/param.h>
#include <sys/kernel.h>
1994-05-24 10:09:53 +00:00
#include <sys/systm.h>
#include <sys/exec.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/jail.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
#include <sys/sx.h>
1994-05-24 10:09:53 +00:00
#include <sys/proc.h>
#include <sys/resourcevar.h>
2001-12-04 01:35:06 +00:00
#include <sys/sbuf.h>
#include <sys/sysent.h>
#include <sys/tty.h>
1994-05-24 10:09:53 +00:00
#include <vm/vm.h>
#include <vm/pmap.h>
#include <vm/vm_param.h>
2001-12-04 01:35:06 +00:00
#include <fs/pseudofs/pseudofs.h>
#include <fs/procfs/procfs.h>
1994-05-24 10:09:53 +00:00
int
2001-12-04 01:35:06 +00:00
procfs_doprocstatus(PFS_FILL_ARGS)
1994-05-24 10:09:53 +00:00
{
struct session *sess;
struct thread *tdfirst;
1994-05-24 10:09:53 +00:00
struct tty *tp;
struct ucred *cr;
const char *wmesg;
2001-12-04 01:35:06 +00:00
char *pc;
1994-05-24 10:09:53 +00:00
char *sep;
int pid, ppid, pgid, sid;
int i;
pid = p->p_pid;
PROC_LOCK(p);
ppid = p->p_pptr ? p->p_pptr->p_pid : 0;
1994-05-24 10:09:53 +00:00
pgid = p->p_pgrp->pg_id;
sess = p->p_pgrp->pg_session;
SESS_LOCK(sess);
1994-05-24 10:09:53 +00:00
sid = sess->s_leader ? sess->s_leader->p_pid : 0;
/* comm pid ppid pgid sid tty ctty,sldr start ut st wmsg
2003-12-07 17:40:00 +00:00
euid ruid rgid,egid,groups[1 .. NGROUPS]
1996-02-02 05:19:20 +00:00
*/
2000-11-08 21:53:05 +00:00
pc = p->p_comm;
do {
if (*pc < 33 || *pc > 126 || *pc == '\\')
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, "\\%03o", *pc);
else
2001-12-04 01:35:06 +00:00
sbuf_putc(sb, *pc);
} while (*++pc);
sbuf_printf(sb, " %d %d %d %d ", pid, ppid, pgid, sid);
if ((p->p_flag & P_CONTROLT) && (tp = sess->s_ttyp))
sbuf_printf(sb, "%s ", devtoname(tp->t_dev));
1994-05-24 10:09:53 +00:00
else
sbuf_printf(sb, "- ");
1994-05-24 10:09:53 +00:00
sep = "";
if (sess->s_ttyvp) {
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, "%sctty", sep);
1994-05-24 10:09:53 +00:00
sep = ",";
}
if (SESS_LEADER(p)) {
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, "%ssldr", sep);
1994-05-24 10:09:53 +00:00
sep = ",";
2000-11-08 21:53:05 +00:00
}
SESS_UNLOCK(sess);
2000-11-08 21:53:05 +00:00
if (*sep != ',') {
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, "noflags");
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);
if (p->p_flag & P_SA)
wmesg = "-kse- ";
else {
tdfirst = FIRST_THREAD_IN_PROC(p);
if (tdfirst->td_wchan != NULL) {
KASSERT(tdfirst->td_wmesg != NULL,
("wchan %p has no wmesg", tdfirst->td_wchan));
wmesg = tdfirst->td_wmesg;
} else
wmesg = "nochan";
}
Rework how we store process times in the kernel such that we always store the raw values including for child process statistics and only compute the system and user timevals on demand. - Fix the various kern_wait() syscall wrappers to only pass in a rusage pointer if they are going to use the result. - Add a kern_getrusage() function for the ABI syscalls to use so that they don't have to play stackgap games to call getrusage(). - Fix the svr4_sys_times() syscall to just call calcru() to calculate the times it needs rather than calling getrusage() twice with associated stackgap, etc. - Add a new rusage_ext structure to store raw time stats such as tick counts for user, system, and interrupt time as well as a bintime of the total runtime. A new p_rux field in struct proc replaces the same inline fields from struct proc (i.e. p_[isu]ticks, p_[isu]u, and p_runtime). A new p_crux field in struct proc contains the "raw" child time usage statistics. ruadd() has been changed to handle adding the associated rusage_ext structures as well as the values in rusage. Effectively, the values in rusage_ext replace the ru_utime and ru_stime values in struct rusage. These two fields in struct rusage are no longer used in the kernel. - calcru() has been split into a static worker function calcru1() that calculates appropriate timevals for user and system time as well as updating the rux_[isu]u fields of a passed in rusage_ext structure. calcru() uses a copy of the process' p_rux structure to compute the timevals after updating the runtime appropriately if any of the threads in that process are currently executing. It also now only locks sched_lock internally while doing the rux_runtime fixup. calcru() now only requires the caller to hold the proc lock and calcru1() only requires the proc lock internally. calcru() also no longer allows callers to ask for an interrupt timeval since none of them actually did. - calcru() now correctly handles threads executing on other CPUs. - A new calccru() function computes the child system and user timevals by calling calcru1() on p_crux. Note that this means that any code that wants child times must now call this function rather than reading from p_cru directly. This function also requires the proc lock. - This finishes the locking for rusage and friends so some of the Giant locks in exit1() and kern_wait() are now gone. - The locking in ttyinfo() has been tweaked so that a shared lock of the proctree lock is used to protect the process group rather than the process group lock. By holding this lock until the end of the function we now ensure that the process/thread that we pick to dump info about will no longer vanish while we are trying to output its info to the console. Submitted by: bde (mostly) MFC after: 1 month
2004-10-05 18:51:11 +00:00
mtx_unlock_spin(&sched_lock);
2001-01-24 11:20:05 +00:00
if (p->p_sflag & PS_INMEM) {
struct timeval start, ut, st;
1994-05-24 10:09:53 +00:00
Rework how we store process times in the kernel such that we always store the raw values including for child process statistics and only compute the system and user timevals on demand. - Fix the various kern_wait() syscall wrappers to only pass in a rusage pointer if they are going to use the result. - Add a kern_getrusage() function for the ABI syscalls to use so that they don't have to play stackgap games to call getrusage(). - Fix the svr4_sys_times() syscall to just call calcru() to calculate the times it needs rather than calling getrusage() twice with associated stackgap, etc. - Add a new rusage_ext structure to store raw time stats such as tick counts for user, system, and interrupt time as well as a bintime of the total runtime. A new p_rux field in struct proc replaces the same inline fields from struct proc (i.e. p_[isu]ticks, p_[isu]u, and p_runtime). A new p_crux field in struct proc contains the "raw" child time usage statistics. ruadd() has been changed to handle adding the associated rusage_ext structures as well as the values in rusage. Effectively, the values in rusage_ext replace the ru_utime and ru_stime values in struct rusage. These two fields in struct rusage are no longer used in the kernel. - calcru() has been split into a static worker function calcru1() that calculates appropriate timevals for user and system time as well as updating the rux_[isu]u fields of a passed in rusage_ext structure. calcru() uses a copy of the process' p_rux structure to compute the timevals after updating the runtime appropriately if any of the threads in that process are currently executing. It also now only locks sched_lock internally while doing the rux_runtime fixup. calcru() now only requires the caller to hold the proc lock and calcru1() only requires the proc lock internally. calcru() also no longer allows callers to ask for an interrupt timeval since none of them actually did. - calcru() now correctly handles threads executing on other CPUs. - A new calccru() function computes the child system and user timevals by calling calcru1() on p_crux. Note that this means that any code that wants child times must now call this function rather than reading from p_cru directly. This function also requires the proc lock. - This finishes the locking for rusage and friends so some of the Giant locks in exit1() and kern_wait() are now gone. - The locking in ttyinfo() has been tweaked so that a shared lock of the proctree lock is used to protect the process group rather than the process group lock. By holding this lock until the end of the function we now ensure that the process/thread that we pick to dump info about will no longer vanish while we are trying to output its info to the console. Submitted by: bde (mostly) MFC after: 1 month
2004-10-05 18:51:11 +00:00
calcru(p, &ut, &st);
start = p->p_stats->p_start;
timevaladd(&start, &boottime);
sbuf_printf(sb, " %jd,%ld %jd,%ld %jd,%ld",
(intmax_t)start.tv_sec, start.tv_usec,
(intmax_t)ut.tv_sec, ut.tv_usec,
(intmax_t)st.tv_sec, st.tv_usec);
2001-01-24 11:20:05 +00:00
} else {
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, " -1,-1 -1,-1 -1,-1");
2001-01-24 11:20:05 +00:00
}
1994-05-24 10:09:53 +00:00
sbuf_printf(sb, " %s", wmesg);
1994-05-24 10:09:53 +00:00
cr = p->p_ucred;
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, " %lu %lu %lu",
1998-07-11 07:46:16 +00:00
(u_long)cr->cr_uid,
o Merge contents of struct pcred into struct ucred. Specifically, add the real uid, saved uid, real gid, and saved gid to ucred, as well as the pcred->pc_uidinfo, which was associated with the real uid, only rename it to cr_ruidinfo so as not to conflict with cr_uidinfo, which corresponds to the effective uid. o Remove p_cred from struct proc; add p_ucred to struct proc, replacing original macro that pointed. p->p_ucred to p->p_cred->pc_ucred. o Universally update code so that it makes use of ucred instead of pcred, p->p_ucred instead of p->p_pcred, cr_ruidinfo instead of p_uidinfo, cr_{r,sv}{u,g}id instead of p_*, etc. o Remove pcred0 and its initialization from init_main.c; initialize cr_ruidinfo there. o Restruction many credential modification chunks to always crdup while we figure out locking and optimizations; generally speaking, this means moving to a structure like this: newcred = crdup(oldcred); ... p->p_ucred = newcred; crfree(oldcred); It's not race-free, but better than nothing. There are also races in sys_process.c, all inter-process authorization, fork, exec, and exit. o Remove sigio->sio_ruid since sigio->sio_ucred now contains the ruid; remove comments indicating that the old arrangement was a problem. o Restructure exec1() a little to use newcred/oldcred arrangement, and use improved uid management primitives. o Clean up exit1() so as to do less work in credential cleanup due to pcred removal. o Clean up fork1() so as to do less work in credential cleanup and allocation. o Clean up ktrcanset() to take into account changes, and move to using suser_xxx() instead of performing a direct uid==0 comparision. o Improve commenting in various kern_prot.c credential modification calls to better document current behavior. In a couple of places, current behavior is a little questionable and we need to check POSIX.1 to make sure it's "right". More commenting work still remains to be done. o Update credential management calls, such as crfree(), to take into account new ruidinfo reference. o Modify or add the following uid and gid helper routines: change_euid() change_egid() change_ruid() change_rgid() change_svuid() change_svgid() In each case, the call now acts on a credential not a process, and as such no longer requires more complicated process locking/etc. They now assume the caller will do any necessary allocation of an exclusive credential reference. Each is commented to document its reference requirements. o CANSIGIO() is simplified to require only credentials, not processes and pcreds. o Remove lots of (p_pcred==NULL) checks. o Add an XXX to authorization code in nfs_lock.c, since it's questionable, and needs to be considered carefully. o Simplify posix4 authorization code to require only credentials, not processes and pcreds. Note that this authorization, as well as CANSIGIO(), needs to be updated to use the p_cansignal() and p_cansched() centralized authorization routines, as they currently do not take into account some desirable restrictions that are handled by the centralized routines, as well as being inconsistent with other similar authorization instances. o Update libkvm to take these changes into account. Obtained from: TrustedBSD Project Reviewed by: green, bde, jhb, freebsd-arch, freebsd-audit
2001-05-25 16:59:11 +00:00
(u_long)cr->cr_ruid,
(u_long)cr->cr_rgid);
1996-02-02 05:19:20 +00:00
2003-12-07 17:40:00 +00:00
/* egid (cr->cr_svgid) is equal to cr_ngroups[0]
1996-02-02 05:19:20 +00:00
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++) {
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, ",%lu", (u_long)cr->cr_groups[i]);
2000-11-08 21:53:05 +00:00
}
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)) {
mtx_lock(&p->p_ucred->cr_prison->pr_mtx);
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, " %s", p->p_ucred->cr_prison->pr_host);
mtx_unlock(&p->p_ucred->cr_prison->pr_mtx);
} else {
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, " -");
}
PROC_UNLOCK(p);
2001-12-04 01:35:06 +00:00
sbuf_printf(sb, "\n");
2000-11-08 21:53:05 +00:00
2001-12-04 01:35:06 +00:00
return (0);
1994-05-24 10:09:53 +00:00
}
int
2001-12-04 01:35:06 +00:00
procfs_doproccmdline(PFS_FILL_ARGS)
{
struct ps_strings pstr;
char **ps_argvstr;
2001-12-04 01:35:06 +00:00
int error, i;
/*
* 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.
*/
PROC_LOCK(p);
if (p->p_args && p_cansee(td, p) == 0) {
sbuf_bcpy(sb, p->p_args->ar_args, p->p_args->ar_length);
PROC_UNLOCK(p);
return (0);
}
PROC_UNLOCK(p);
if (p != td->td_proc) {
sbuf_printf(sb, "%.*s", MAXCOMLEN, p->p_comm);
} else {
error = copyin((void *)p->p_sysent->sv_psstrings, &pstr,
sizeof(pstr));
if (error)
return (error);
if (pstr.ps_nargvstr > ARG_MAX)
return (E2BIG);
ps_argvstr = malloc(pstr.ps_nargvstr * sizeof(char *),
M_TEMP, M_WAITOK);
error = copyin((void *)pstr.ps_argvstr, ps_argvstr,
pstr.ps_nargvstr * sizeof(char *));
if (error) {
free(ps_argvstr, M_TEMP);
return (error);
}
for (i = 0; i < pstr.ps_nargvstr; i++) {
sbuf_copyin(sb, ps_argvstr[i], 0);
sbuf_printf(sb, "%c", '\0');
}
free(ps_argvstr, M_TEMP);
}
2001-12-04 01:35:06 +00:00
return (0);
}