linux/fs/proc/array.c
Andy Lutomirski 58319057b7 capabilities: ambient capabilities
Credit where credit is due: this idea comes from Christoph Lameter with
a lot of valuable input from Serge Hallyn.  This patch is heavily based
on Christoph's patch.

===== The status quo =====

On Linux, there are a number of capabilities defined by the kernel.  To
perform various privileged tasks, processes can wield capabilities that
they hold.

Each task has four capability masks: effective (pE), permitted (pP),
inheritable (pI), and a bounding set (X).  When the kernel checks for a
capability, it checks pE.  The other capability masks serve to modify
what capabilities can be in pE.

Any task can remove capabilities from pE, pP, or pI at any time.  If a
task has a capability in pP, it can add that capability to pE and/or pI.
If a task has CAP_SETPCAP, then it can add any capability to pI, and it
can remove capabilities from X.

Tasks are not the only things that can have capabilities; files can also
have capabilities.  A file can have no capabilty information at all [1].
If a file has capability information, then it has a permitted mask (fP)
and an inheritable mask (fI) as well as a single effective bit (fE) [2].
File capabilities modify the capabilities of tasks that execve(2) them.

A task that successfully calls execve has its capabilities modified for
the file ultimately being excecuted (i.e.  the binary itself if that
binary is ELF or for the interpreter if the binary is a script.) [3] In
the capability evolution rules, for each mask Z, pZ represents the old
value and pZ' represents the new value.  The rules are:

  pP' = (X & fP) | (pI & fI)
  pI' = pI
  pE' = (fE ? pP' : 0)
  X is unchanged

For setuid binaries, fP, fI, and fE are modified by a moderately
complicated set of rules that emulate POSIX behavior.  Similarly, if
euid == 0 or ruid == 0, then fP, fI, and fE are modified differently
(primary, fP and fI usually end up being the full set).  For nonroot
users executing binaries with neither setuid nor file caps, fI and fP
are empty and fE is false.

As an extra complication, if you execute a process as nonroot and fE is
set, then the "secure exec" rules are in effect: AT_SECURE gets set,
LD_PRELOAD doesn't work, etc.

This is rather messy.  We've learned that making any changes is
dangerous, though: if a new kernel version allows an unprivileged
program to change its security state in a way that persists cross
execution of a setuid program or a program with file caps, this
persistent state is surprisingly likely to allow setuid or file-capped
programs to be exploited for privilege escalation.

===== The problem =====

Capability inheritance is basically useless.

If you aren't root and you execute an ordinary binary, fI is zero, so
your capabilities have no effect whatsoever on pP'.  This means that you
can't usefully execute a helper process or a shell command with elevated
capabilities if you aren't root.

On current kernels, you can sort of work around this by setting fI to
the full set for most or all non-setuid executable files.  This causes
pP' = pI for nonroot, and inheritance works.  No one does this because
it's a PITA and it isn't even supported on most filesystems.

If you try this, you'll discover that every nonroot program ends up with
secure exec rules, breaking many things.

This is a problem that has bitten many people who have tried to use
capabilities for anything useful.

===== The proposed change =====

This patch adds a fifth capability mask called the ambient mask (pA).
pA does what most people expect pI to do.

pA obeys the invariant that no bit can ever be set in pA if it is not
set in both pP and pI.  Dropping a bit from pP or pI drops that bit from
pA.  This ensures that existing programs that try to drop capabilities
still do so, with a complication.  Because capability inheritance is so
broken, setting KEEPCAPS, using setresuid to switch to nonroot uids, and
then calling execve effectively drops capabilities.  Therefore,
setresuid from root to nonroot conditionally clears pA unless
SECBIT_NO_SETUID_FIXUP is set.  Processes that don't like this can
re-add bits to pA afterwards.

The capability evolution rules are changed:

  pA' = (file caps or setuid or setgid ? 0 : pA)
  pP' = (X & fP) | (pI & fI) | pA'
  pI' = pI
  pE' = (fE ? pP' : pA')
  X is unchanged

If you are nonroot but you have a capability, you can add it to pA.  If
you do so, your children get that capability in pA, pP, and pE.  For
example, you can set pA = CAP_NET_BIND_SERVICE, and your children can
automatically bind low-numbered ports.  Hallelujah!

Unprivileged users can create user namespaces, map themselves to a
nonzero uid, and create both privileged (relative to their namespace)
and unprivileged process trees.  This is currently more or less
impossible.  Hallelujah!

You cannot use pA to try to subvert a setuid, setgid, or file-capped
program: if you execute any such program, pA gets cleared and the
resulting evolution rules are unchanged by this patch.

Users with nonzero pA are unlikely to unintentionally leak that
capability.  If they run programs that try to drop privileges, dropping
privileges will still work.

It's worth noting that the degree of paranoia in this patch could
possibly be reduced without causing serious problems.  Specifically, if
we allowed pA to persist across executing non-pA-aware setuid binaries
and across setresuid, then, naively, the only capabilities that could
leak as a result would be the capabilities in pA, and any attacker
*already* has those capabilities.  This would make me nervous, though --
setuid binaries that tried to privilege-separate might fail to do so,
and putting CAP_DAC_READ_SEARCH or CAP_DAC_OVERRIDE into pA could have
unexpected side effects.  (Whether these unexpected side effects would
be exploitable is an open question.) I've therefore taken the more
paranoid route.  We can revisit this later.

An alternative would be to require PR_SET_NO_NEW_PRIVS before setting
ambient capabilities.  I think that this would be annoying and would
make granting otherwise unprivileged users minor ambient capabilities
(CAP_NET_BIND_SERVICE or CAP_NET_RAW for example) much less useful than
it is with this patch.

===== Footnotes =====

[1] Files that are missing the "security.capability" xattr or that have
unrecognized values for that xattr end up with has_cap set to false.
The code that does that appears to be complicated for no good reason.

[2] The libcap capability mask parsers and formatters are dangerously
misleading and the documentation is flat-out wrong.  fE is *not* a mask;
it's a single bit.  This has probably confused every single person who
has tried to use file capabilities.

[3] Linux very confusingly processes both the script and the interpreter
if applicable, for reasons that elude me.  The results from thinking
about a script's file capabilities and/or setuid bits are mostly
discarded.

Preliminary userspace code is here, but it needs updating:
https://git.kernel.org/cgit/linux/kernel/git/luto/util-linux-playground.git/commit/?h=cap_ambient&id=7f5afbd175d2

Here is a test program that can be used to verify the functionality
(from Christoph):

/*
 * Test program for the ambient capabilities. This program spawns a shell
 * that allows running processes with a defined set of capabilities.
 *
 * (C) 2015 Christoph Lameter <cl@linux.com>
 * Released under: GPL v3 or later.
 *
 *
 * Compile using:
 *
 *	gcc -o ambient_test ambient_test.o -lcap-ng
 *
 * This program must have the following capabilities to run properly:
 * Permissions for CAP_NET_RAW, CAP_NET_ADMIN, CAP_SYS_NICE
 *
 * A command to equip the binary with the right caps is:
 *
 *	setcap cap_net_raw,cap_net_admin,cap_sys_nice+p ambient_test
 *
 *
 * To get a shell with additional caps that can be inherited by other processes:
 *
 *	./ambient_test /bin/bash
 *
 *
 * Verifying that it works:
 *
 * From the bash spawed by ambient_test run
 *
 *	cat /proc/$$/status
 *
 * and have a look at the capabilities.
 */

#include <stdlib.h>
#include <stdio.h>
#include <errno.h>
#include <cap-ng.h>
#include <sys/prctl.h>
#include <linux/capability.h>

/*
 * Definitions from the kernel header files. These are going to be removed
 * when the /usr/include files have these defined.
 */
#define PR_CAP_AMBIENT 47
#define PR_CAP_AMBIENT_IS_SET 1
#define PR_CAP_AMBIENT_RAISE 2
#define PR_CAP_AMBIENT_LOWER 3
#define PR_CAP_AMBIENT_CLEAR_ALL 4

static void set_ambient_cap(int cap)
{
	int rc;

	capng_get_caps_process();
	rc = capng_update(CAPNG_ADD, CAPNG_INHERITABLE, cap);
	if (rc) {
		printf("Cannot add inheritable cap\n");
		exit(2);
	}
	capng_apply(CAPNG_SELECT_CAPS);

	/* Note the two 0s at the end. Kernel checks for these */
	if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, cap, 0, 0)) {
		perror("Cannot set cap");
		exit(1);
	}
}

int main(int argc, char **argv)
{
	int rc;

	set_ambient_cap(CAP_NET_RAW);
	set_ambient_cap(CAP_NET_ADMIN);
	set_ambient_cap(CAP_SYS_NICE);

	printf("Ambient_test forking shell\n");
	if (execv(argv[1], argv + 1))
		perror("Cannot exec");

	return 0;
}

Signed-off-by: Christoph Lameter <cl@linux.com> # Original author
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Aaron Jones <aaronmdjones@gmail.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Andrew G. Morgan <morgan@kernel.org>
Cc: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Austin S Hemmelgarn <ahferroin7@gmail.com>
Cc: Markku Savela <msa@moth.iki.fi>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: James Morris <james.l.morris@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 16:54:41 -07:00

707 lines
18 KiB
C

/*
* linux/fs/proc/array.c
*
* Copyright (C) 1992 by Linus Torvalds
* based on ideas by Darren Senn
*
* Fixes:
* Michael. K. Johnson: stat,statm extensions.
* <johnsonm@stolaf.edu>
*
* Pauline Middelink : Made cmdline,envline only break at '\0's, to
* make sure SET_PROCTITLE works. Also removed
* bad '!' which forced address recalculation for
* EVERY character on the current page.
* <middelin@polyware.iaf.nl>
*
* Danny ter Haar : added cpuinfo
* <dth@cistron.nl>
*
* Alessandro Rubini : profile extension.
* <rubini@ipvvis.unipv.it>
*
* Jeff Tranter : added BogoMips field to cpuinfo
* <Jeff_Tranter@Mitel.COM>
*
* Bruno Haible : remove 4K limit for the maps file
* <haible@ma2s2.mathematik.uni-karlsruhe.de>
*
* Yves Arrouye : remove removal of trailing spaces in get_array.
* <Yves.Arrouye@marin.fdn.fr>
*
* Jerome Forissier : added per-CPU time information to /proc/stat
* and /proc/<pid>/cpu extension
* <forissier@isia.cma.fr>
* - Incorporation and non-SMP safe operation
* of forissier patch in 2.1.78 by
* Hans Marcus <crowbar@concepts.nl>
*
* aeb@cwi.nl : /proc/partitions
*
*
* Alan Cox : security fixes.
* <alan@lxorguk.ukuu.org.uk>
*
* Al Viro : safe handling of mm_struct
*
* Gerhard Wichert : added BIGMEM support
* Siemens AG <Gerhard.Wichert@pdb.siemens.de>
*
* Al Viro & Jeff Garzik : moved most of the thing into base.c and
* : proc_misc.c. The rest may eventually go into
* : base.c too.
*/
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/tty.h>
#include <linux/string.h>
#include <linux/mman.h>
#include <linux/proc_fs.h>
#include <linux/ioport.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/signal.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/times.h>
#include <linux/cpuset.h>
#include <linux/rcupdate.h>
#include <linux/delayacct.h>
#include <linux/seq_file.h>
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/string_helpers.h>
#include <linux/user_namespace.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include "internal.h"
static inline void task_name(struct seq_file *m, struct task_struct *p)
{
char *buf;
char tcomm[sizeof(p->comm)];
get_task_comm(tcomm, p);
seq_puts(m, "Name:\t");
buf = m->buf + m->count;
/* Ignore error for now */
buf += string_escape_str(tcomm, buf, m->size - m->count,
ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
m->count = buf - m->buf;
seq_putc(m, '\n');
}
/*
* The task state array is a strange "bitmap" of
* reasons to sleep. Thus "running" is zero, and
* you can test for combinations of others with
* simple bit tests.
*/
static const char * const task_state_array[] = {
"R (running)", /* 0 */
"S (sleeping)", /* 1 */
"D (disk sleep)", /* 2 */
"T (stopped)", /* 4 */
"t (tracing stop)", /* 8 */
"X (dead)", /* 16 */
"Z (zombie)", /* 32 */
};
static inline const char *get_task_state(struct task_struct *tsk)
{
unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
/*
* Parked tasks do not run; they sit in __kthread_parkme().
* Without this check, we would report them as running, which is
* clearly wrong, so we report them as sleeping instead.
*/
if (tsk->state == TASK_PARKED)
state = TASK_INTERRUPTIBLE;
BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
return task_state_array[fls(state)];
}
static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *p)
{
struct user_namespace *user_ns = seq_user_ns(m);
struct group_info *group_info;
int g;
struct task_struct *tracer;
const struct cred *cred;
pid_t ppid, tpid = 0, tgid, ngid;
unsigned int max_fds = 0;
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
tracer = ptrace_parent(p);
if (tracer)
tpid = task_pid_nr_ns(tracer, ns);
tgid = task_tgid_nr_ns(p, ns);
ngid = task_numa_group_id(p);
cred = get_task_cred(p);
task_lock(p);
if (p->files)
max_fds = files_fdtable(p->files)->max_fds;
task_unlock(p);
rcu_read_unlock();
seq_printf(m,
"State:\t%s\n"
"Tgid:\t%d\n"
"Ngid:\t%d\n"
"Pid:\t%d\n"
"PPid:\t%d\n"
"TracerPid:\t%d\n"
"Uid:\t%d\t%d\t%d\t%d\n"
"Gid:\t%d\t%d\t%d\t%d\n"
"FDSize:\t%d\nGroups:\t",
get_task_state(p),
tgid, ngid, pid_nr_ns(pid, ns), ppid, tpid,
from_kuid_munged(user_ns, cred->uid),
from_kuid_munged(user_ns, cred->euid),
from_kuid_munged(user_ns, cred->suid),
from_kuid_munged(user_ns, cred->fsuid),
from_kgid_munged(user_ns, cred->gid),
from_kgid_munged(user_ns, cred->egid),
from_kgid_munged(user_ns, cred->sgid),
from_kgid_munged(user_ns, cred->fsgid),
max_fds);
group_info = cred->group_info;
for (g = 0; g < group_info->ngroups; g++)
seq_printf(m, "%d ",
from_kgid_munged(user_ns, GROUP_AT(group_info, g)));
put_cred(cred);
#ifdef CONFIG_PID_NS
seq_puts(m, "\nNStgid:");
for (g = ns->level; g <= pid->level; g++)
seq_printf(m, "\t%d",
task_tgid_nr_ns(p, pid->numbers[g].ns));
seq_puts(m, "\nNSpid:");
for (g = ns->level; g <= pid->level; g++)
seq_printf(m, "\t%d",
task_pid_nr_ns(p, pid->numbers[g].ns));
seq_puts(m, "\nNSpgid:");
for (g = ns->level; g <= pid->level; g++)
seq_printf(m, "\t%d",
task_pgrp_nr_ns(p, pid->numbers[g].ns));
seq_puts(m, "\nNSsid:");
for (g = ns->level; g <= pid->level; g++)
seq_printf(m, "\t%d",
task_session_nr_ns(p, pid->numbers[g].ns));
#endif
seq_putc(m, '\n');
}
void render_sigset_t(struct seq_file *m, const char *header,
sigset_t *set)
{
int i;
seq_puts(m, header);
i = _NSIG;
do {
int x = 0;
i -= 4;
if (sigismember(set, i+1)) x |= 1;
if (sigismember(set, i+2)) x |= 2;
if (sigismember(set, i+3)) x |= 4;
if (sigismember(set, i+4)) x |= 8;
seq_printf(m, "%x", x);
} while (i >= 4);
seq_putc(m, '\n');
}
static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
sigset_t *catch)
{
struct k_sigaction *k;
int i;
k = p->sighand->action;
for (i = 1; i <= _NSIG; ++i, ++k) {
if (k->sa.sa_handler == SIG_IGN)
sigaddset(ign, i);
else if (k->sa.sa_handler != SIG_DFL)
sigaddset(catch, i);
}
}
static inline void task_sig(struct seq_file *m, struct task_struct *p)
{
unsigned long flags;
sigset_t pending, shpending, blocked, ignored, caught;
int num_threads = 0;
unsigned long qsize = 0;
unsigned long qlim = 0;
sigemptyset(&pending);
sigemptyset(&shpending);
sigemptyset(&blocked);
sigemptyset(&ignored);
sigemptyset(&caught);
if (lock_task_sighand(p, &flags)) {
pending = p->pending.signal;
shpending = p->signal->shared_pending.signal;
blocked = p->blocked;
collect_sigign_sigcatch(p, &ignored, &caught);
num_threads = get_nr_threads(p);
rcu_read_lock(); /* FIXME: is this correct? */
qsize = atomic_read(&__task_cred(p)->user->sigpending);
rcu_read_unlock();
qlim = task_rlimit(p, RLIMIT_SIGPENDING);
unlock_task_sighand(p, &flags);
}
seq_printf(m, "Threads:\t%d\n", num_threads);
seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
/* render them all */
render_sigset_t(m, "SigPnd:\t", &pending);
render_sigset_t(m, "ShdPnd:\t", &shpending);
render_sigset_t(m, "SigBlk:\t", &blocked);
render_sigset_t(m, "SigIgn:\t", &ignored);
render_sigset_t(m, "SigCgt:\t", &caught);
}
static void render_cap_t(struct seq_file *m, const char *header,
kernel_cap_t *a)
{
unsigned __capi;
seq_puts(m, header);
CAP_FOR_EACH_U32(__capi) {
seq_printf(m, "%08x",
a->cap[CAP_LAST_U32 - __capi]);
}
seq_putc(m, '\n');
}
static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
const struct cred *cred;
kernel_cap_t cap_inheritable, cap_permitted, cap_effective,
cap_bset, cap_ambient;
rcu_read_lock();
cred = __task_cred(p);
cap_inheritable = cred->cap_inheritable;
cap_permitted = cred->cap_permitted;
cap_effective = cred->cap_effective;
cap_bset = cred->cap_bset;
cap_ambient = cred->cap_ambient;
rcu_read_unlock();
render_cap_t(m, "CapInh:\t", &cap_inheritable);
render_cap_t(m, "CapPrm:\t", &cap_permitted);
render_cap_t(m, "CapEff:\t", &cap_effective);
render_cap_t(m, "CapBnd:\t", &cap_bset);
render_cap_t(m, "CapAmb:\t", &cap_ambient);
}
static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
{
#ifdef CONFIG_SECCOMP
seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode);
#endif
}
static inline void task_context_switch_counts(struct seq_file *m,
struct task_struct *p)
{
seq_printf(m, "voluntary_ctxt_switches:\t%lu\n"
"nonvoluntary_ctxt_switches:\t%lu\n",
p->nvcsw,
p->nivcsw);
}
static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
{
seq_printf(m, "Cpus_allowed:\t%*pb\n",
cpumask_pr_args(&task->cpus_allowed));
seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
cpumask_pr_args(&task->cpus_allowed));
}
int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
struct mm_struct *mm = get_task_mm(task);
task_name(m, task);
task_state(m, ns, pid, task);
if (mm) {
task_mem(m, mm);
mmput(mm);
}
task_sig(m, task);
task_cap(m, task);
task_seccomp(m, task);
task_cpus_allowed(m, task);
cpuset_task_status_allowed(m, task);
task_context_switch_counts(m, task);
return 0;
}
static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task, int whole)
{
unsigned long vsize, eip, esp, wchan = ~0UL;
int priority, nice;
int tty_pgrp = -1, tty_nr = 0;
sigset_t sigign, sigcatch;
char state;
pid_t ppid = 0, pgid = -1, sid = -1;
int num_threads = 0;
int permitted;
struct mm_struct *mm;
unsigned long long start_time;
unsigned long cmin_flt = 0, cmaj_flt = 0;
unsigned long min_flt = 0, maj_flt = 0;
cputime_t cutime, cstime, utime, stime;
cputime_t cgtime, gtime;
unsigned long rsslim = 0;
char tcomm[sizeof(task->comm)];
unsigned long flags;
state = *get_task_state(task);
vsize = eip = esp = 0;
permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
if (permitted) {
eip = KSTK_EIP(task);
esp = KSTK_ESP(task);
}
}
get_task_comm(tcomm, task);
sigemptyset(&sigign);
sigemptyset(&sigcatch);
cutime = cstime = utime = stime = 0;
cgtime = gtime = 0;
if (lock_task_sighand(task, &flags)) {
struct signal_struct *sig = task->signal;
if (sig->tty) {
struct pid *pgrp = tty_get_pgrp(sig->tty);
tty_pgrp = pid_nr_ns(pgrp, ns);
put_pid(pgrp);
tty_nr = new_encode_dev(tty_devnum(sig->tty));
}
num_threads = get_nr_threads(task);
collect_sigign_sigcatch(task, &sigign, &sigcatch);
cmin_flt = sig->cmin_flt;
cmaj_flt = sig->cmaj_flt;
cutime = sig->cutime;
cstime = sig->cstime;
cgtime = sig->cgtime;
rsslim = ACCESS_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
/* add up live thread stats at the group level */
if (whole) {
struct task_struct *t = task;
do {
min_flt += t->min_flt;
maj_flt += t->maj_flt;
gtime += task_gtime(t);
} while_each_thread(task, t);
min_flt += sig->min_flt;
maj_flt += sig->maj_flt;
thread_group_cputime_adjusted(task, &utime, &stime);
gtime += sig->gtime;
}
sid = task_session_nr_ns(task, ns);
ppid = task_tgid_nr_ns(task->real_parent, ns);
pgid = task_pgrp_nr_ns(task, ns);
unlock_task_sighand(task, &flags);
}
if (permitted && (!whole || num_threads < 2))
wchan = get_wchan(task);
if (!whole) {
min_flt = task->min_flt;
maj_flt = task->maj_flt;
task_cputime_adjusted(task, &utime, &stime);
gtime = task_gtime(task);
}
/* scale priority and nice values from timeslices to -20..20 */
/* to make it look like a "normal" Unix priority/nice value */
priority = task_prio(task);
nice = task_nice(task);
/* convert nsec -> ticks */
start_time = nsec_to_clock_t(task->real_start_time);
seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state);
seq_put_decimal_ll(m, ' ', ppid);
seq_put_decimal_ll(m, ' ', pgid);
seq_put_decimal_ll(m, ' ', sid);
seq_put_decimal_ll(m, ' ', tty_nr);
seq_put_decimal_ll(m, ' ', tty_pgrp);
seq_put_decimal_ull(m, ' ', task->flags);
seq_put_decimal_ull(m, ' ', min_flt);
seq_put_decimal_ull(m, ' ', cmin_flt);
seq_put_decimal_ull(m, ' ', maj_flt);
seq_put_decimal_ull(m, ' ', cmaj_flt);
seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime));
seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime));
seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime));
seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime));
seq_put_decimal_ll(m, ' ', priority);
seq_put_decimal_ll(m, ' ', nice);
seq_put_decimal_ll(m, ' ', num_threads);
seq_put_decimal_ull(m, ' ', 0);
seq_put_decimal_ull(m, ' ', start_time);
seq_put_decimal_ull(m, ' ', vsize);
seq_put_decimal_ull(m, ' ', mm ? get_mm_rss(mm) : 0);
seq_put_decimal_ull(m, ' ', rsslim);
seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0);
seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0);
seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0);
seq_put_decimal_ull(m, ' ', esp);
seq_put_decimal_ull(m, ' ', eip);
/* The signal information here is obsolete.
* It must be decimal for Linux 2.0 compatibility.
* Use /proc/#/status for real-time signals.
*/
seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL);
seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL);
seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL);
seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL);
seq_put_decimal_ull(m, ' ', wchan);
seq_put_decimal_ull(m, ' ', 0);
seq_put_decimal_ull(m, ' ', 0);
seq_put_decimal_ll(m, ' ', task->exit_signal);
seq_put_decimal_ll(m, ' ', task_cpu(task));
seq_put_decimal_ull(m, ' ', task->rt_priority);
seq_put_decimal_ull(m, ' ', task->policy);
seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task));
seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime));
seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime));
if (mm && permitted) {
seq_put_decimal_ull(m, ' ', mm->start_data);
seq_put_decimal_ull(m, ' ', mm->end_data);
seq_put_decimal_ull(m, ' ', mm->start_brk);
seq_put_decimal_ull(m, ' ', mm->arg_start);
seq_put_decimal_ull(m, ' ', mm->arg_end);
seq_put_decimal_ull(m, ' ', mm->env_start);
seq_put_decimal_ull(m, ' ', mm->env_end);
} else
seq_printf(m, " 0 0 0 0 0 0 0");
if (permitted)
seq_put_decimal_ll(m, ' ', task->exit_code);
else
seq_put_decimal_ll(m, ' ', 0);
seq_putc(m, '\n');
if (mm)
mmput(mm);
return 0;
}
int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
return do_task_stat(m, ns, pid, task, 0);
}
int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
return do_task_stat(m, ns, pid, task, 1);
}
int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
unsigned long size = 0, resident = 0, shared = 0, text = 0, data = 0;
struct mm_struct *mm = get_task_mm(task);
if (mm) {
size = task_statm(mm, &shared, &text, &data, &resident);
mmput(mm);
}
/*
* For quick read, open code by putting numbers directly
* expected format is
* seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
* size, resident, shared, text, data);
*/
seq_put_decimal_ull(m, 0, size);
seq_put_decimal_ull(m, ' ', resident);
seq_put_decimal_ull(m, ' ', shared);
seq_put_decimal_ull(m, ' ', text);
seq_put_decimal_ull(m, ' ', 0);
seq_put_decimal_ull(m, ' ', data);
seq_put_decimal_ull(m, ' ', 0);
seq_putc(m, '\n');
return 0;
}
#ifdef CONFIG_PROC_CHILDREN
static struct pid *
get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
{
struct task_struct *start, *task;
struct pid *pid = NULL;
read_lock(&tasklist_lock);
start = pid_task(proc_pid(inode), PIDTYPE_PID);
if (!start)
goto out;
/*
* Lets try to continue searching first, this gives
* us significant speedup on children-rich processes.
*/
if (pid_prev) {
task = pid_task(pid_prev, PIDTYPE_PID);
if (task && task->real_parent == start &&
!(list_empty(&task->sibling))) {
if (list_is_last(&task->sibling, &start->children))
goto out;
task = list_first_entry(&task->sibling,
struct task_struct, sibling);
pid = get_pid(task_pid(task));
goto out;
}
}
/*
* Slow search case.
*
* We might miss some children here if children
* are exited while we were not holding the lock,
* but it was never promised to be accurate that
* much.
*
* "Just suppose that the parent sleeps, but N children
* exit after we printed their tids. Now the slow paths
* skips N extra children, we miss N tasks." (c)
*
* So one need to stop or freeze the leader and all
* its children to get a precise result.
*/
list_for_each_entry(task, &start->children, sibling) {
if (pos-- == 0) {
pid = get_pid(task_pid(task));
break;
}
}
out:
read_unlock(&tasklist_lock);
return pid;
}
static int children_seq_show(struct seq_file *seq, void *v)
{
struct inode *inode = seq->private;
pid_t pid;
pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
seq_printf(seq, "%d ", pid);
return 0;
}
static void *children_seq_start(struct seq_file *seq, loff_t *pos)
{
return get_children_pid(seq->private, NULL, *pos);
}
static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct pid *pid;
pid = get_children_pid(seq->private, v, *pos + 1);
put_pid(v);
++*pos;
return pid;
}
static void children_seq_stop(struct seq_file *seq, void *v)
{
put_pid(v);
}
static const struct seq_operations children_seq_ops = {
.start = children_seq_start,
.next = children_seq_next,
.stop = children_seq_stop,
.show = children_seq_show,
};
static int children_seq_open(struct inode *inode, struct file *file)
{
struct seq_file *m;
int ret;
ret = seq_open(file, &children_seq_ops);
if (ret)
return ret;
m = file->private_data;
m->private = inode;
return ret;
}
int children_seq_release(struct inode *inode, struct file *file)
{
seq_release(inode, file);
return 0;
}
const struct file_operations proc_tid_children_operations = {
.open = children_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = children_seq_release,
};
#endif /* CONFIG_PROC_CHILDREN */