kernel-ark/fs/proc/array.c
Andrew G. Morgan ca05a99a54 capabilities: remain source compatible with 32-bit raw legacy capability support.
Source code out there hard-codes a notion of what the
_LINUX_CAPABILITY_VERSION #define means in terms of the semantics of the
raw capability system calls capget() and capset().  Its unfortunate, but
true.

Since the confusing header file has been in a released kernel, there is
software that is erroneously using 64-bit capabilities with the semantics
of 32-bit compatibilities.  These recently compiled programs may suffer
corruption of their memory when sys_getcap() overwrites more memory than
they are coded to expect, and the raising of added capabilities when using
sys_capset().

As such, this patch does a number of things to clean up the situation
for all. It

  1. forces the _LINUX_CAPABILITY_VERSION define to always retain its
     legacy value.

  2. adopts a new #define strategy for the kernel's internal
     implementation of the preferred magic.

  3. deprecates v2 capability magic in favor of a new (v3) magic
     number. The functionality of v3 is entirely equivalent to v2,
     the only difference being that the v2 magic causes the kernel
     to log a "deprecated" warning so the admin can find applications
     that may be using v2 inappropriately.

[User space code continues to be encouraged to use the libcap API which
protects the application from details like this.  libcap-2.10 is the first
to support v3 capabilities.]

Fixes issue reported in https://bugzilla.redhat.com/show_bug.cgi?id=447518.
Thanks to Bojan Smojver for the report.

[akpm@linux-foundation.org: s/depreciate/deprecate/g]
[akpm@linux-foundation.org: be robust about put_user size]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Andrew G. Morgan <morgan@kernel.org>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Bojan Smojver <bojan@rexursive.com>
Cc: stable@kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
2008-05-31 16:36:16 -07:00

581 lines
14 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.Cox@linux.org>
*
* 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/slab.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 <asm/pgtable.h>
#include <asm/processor.h>
#include "internal.h"
/* Gcc optimizes away "strlen(x)" for constant x */
#define ADDBUF(buffer, string) \
do { memcpy(buffer, string, strlen(string)); \
buffer += strlen(string); } while (0)
static inline void task_name(struct seq_file *m, struct task_struct *p)
{
int i;
char *buf, *end;
char *name;
char tcomm[sizeof(p->comm)];
get_task_comm(tcomm, p);
seq_printf(m, "Name:\t");
end = m->buf + m->size;
buf = m->buf + m->count;
name = tcomm;
i = sizeof(tcomm);
while (i && (buf < end)) {
unsigned char c = *name;
name++;
i--;
*buf = c;
if (!c)
break;
if (c == '\\') {
buf++;
if (buf < end)
*buf++ = c;
continue;
}
if (c == '\n') {
*buf++ = '\\';
if (buf < end)
*buf++ = 'n';
continue;
}
buf++;
}
m->count = buf - m->buf;
seq_printf(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 *task_state_array[] = {
"R (running)", /* 0 */
"S (sleeping)", /* 1 */
"D (disk sleep)", /* 2 */
"T (stopped)", /* 4 */
"T (tracing stop)", /* 8 */
"Z (zombie)", /* 16 */
"X (dead)" /* 32 */
};
static inline const char *get_task_state(struct task_struct *tsk)
{
unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state;
const char **p = &task_state_array[0];
while (state) {
p++;
state >>= 1;
}
return *p;
}
static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *p)
{
struct group_info *group_info;
int g;
struct fdtable *fdt = NULL;
pid_t ppid, tpid;
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
tpid = pid_alive(p) && p->ptrace ?
task_pid_nr_ns(rcu_dereference(p->parent), ns) : 0;
seq_printf(m,
"State:\t%s\n"
"Tgid:\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",
get_task_state(p),
task_tgid_nr_ns(p, ns),
pid_nr_ns(pid, ns),
ppid, tpid,
p->uid, p->euid, p->suid, p->fsuid,
p->gid, p->egid, p->sgid, p->fsgid);
task_lock(p);
if (p->files)
fdt = files_fdtable(p->files);
seq_printf(m,
"FDSize:\t%d\n"
"Groups:\t",
fdt ? fdt->max_fds : 0);
rcu_read_unlock();
group_info = p->group_info;
get_group_info(group_info);
task_unlock(p);
for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
seq_printf(m, "%d ", GROUP_AT(group_info, g));
put_group_info(group_info);
seq_printf(m, "\n");
}
static void render_sigset_t(struct seq_file *m, const char *header,
sigset_t *set)
{
int i;
seq_printf(m, "%s", 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_printf(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);
rcu_read_lock();
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 = atomic_read(&p->signal->count);
qsize = atomic_read(&p->user->sigpending);
qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
unlock_task_sighand(p, &flags);
}
rcu_read_unlock();
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_printf(m, "%s", header);
CAP_FOR_EACH_U32(__capi) {
seq_printf(m, "%08x",
a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
}
seq_printf(m, "\n");
}
static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
render_cap_t(m, "CapInh:\t", &p->cap_inheritable);
render_cap_t(m, "CapPrm:\t", &p->cap_permitted);
render_cap_t(m, "CapEff:\t", &p->cap_effective);
render_cap_t(m, "CapBnd:\t", &p->cap_bset);
}
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);
}
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);
cpuset_task_status_allowed(m, task);
#if defined(CONFIG_S390)
task_show_regs(m, task);
#endif
task_context_switch_counts(m, task);
return 0;
}
/*
* Use precise platform statistics if available:
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
static cputime_t task_utime(struct task_struct *p)
{
return p->utime;
}
static cputime_t task_stime(struct task_struct *p)
{
return p->stime;
}
#else
static cputime_t task_utime(struct task_struct *p)
{
clock_t utime = cputime_to_clock_t(p->utime),
total = utime + cputime_to_clock_t(p->stime);
u64 temp;
/*
* Use CFS's precise accounting:
*/
temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
if (total) {
temp *= utime;
do_div(temp, total);
}
utime = (clock_t)temp;
p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
return p->prev_utime;
}
static cputime_t task_stime(struct task_struct *p)
{
clock_t stime;
/*
* Use CFS's precise accounting. (we subtract utime from
* the total, to make sure the total observed by userspace
* grows monotonically - apps rely on that):
*/
stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
cputime_to_clock_t(task_utime(p));
if (stime >= 0)
p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
return p->prev_stime;
}
#endif
static cputime_t task_gtime(struct task_struct *p)
{
return p->gtime;
}
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;
long 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;
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;
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
eip = KSTK_EIP(task);
esp = KSTK_ESP(task);
}
get_task_comm(tcomm, task);
sigemptyset(&sigign);
sigemptyset(&sigcatch);
cutime = cstime = utime = stime = cputime_zero;
cgtime = gtime = cputime_zero;
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 = atomic_read(&sig->count);
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 = 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;
utime = cputime_add(utime, task_utime(t));
stime = cputime_add(stime, task_stime(t));
gtime = cputime_add(gtime, task_gtime(t));
t = next_thread(t);
} while (t != task);
min_flt += sig->min_flt;
maj_flt += sig->maj_flt;
utime = cputime_add(utime, sig->utime);
stime = cputime_add(stime, sig->stime);
gtime = cputime_add(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 (!whole || num_threads < 2)
wchan = get_wchan(task);
if (!whole) {
min_flt = task->min_flt;
maj_flt = task->maj_flt;
utime = task_utime(task);
stime = task_stime(task);
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);
/* Temporary variable needed for gcc-2.96 */
/* convert timespec -> nsec*/
start_time =
(unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC
+ task->real_start_time.tv_nsec;
/* convert nsec -> ticks */
start_time = nsec_to_clock_t(start_time);
seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
pid_nr_ns(pid, ns),
tcomm,
state,
ppid,
pgid,
sid,
tty_nr,
tty_pgrp,
task->flags,
min_flt,
cmin_flt,
maj_flt,
cmaj_flt,
cputime_to_clock_t(utime),
cputime_to_clock_t(stime),
cputime_to_clock_t(cutime),
cputime_to_clock_t(cstime),
priority,
nice,
num_threads,
start_time,
vsize,
mm ? get_mm_rss(mm) : 0,
rsslim,
mm ? mm->start_code : 0,
mm ? mm->end_code : 0,
mm ? mm->start_stack : 0,
esp,
eip,
/* The signal information here is obsolete.
* It must be decimal for Linux 2.0 compatibility.
* Use /proc/#/status for real-time signals.
*/
task->pending.signal.sig[0] & 0x7fffffffUL,
task->blocked.sig[0] & 0x7fffffffUL,
sigign .sig[0] & 0x7fffffffUL,
sigcatch .sig[0] & 0x7fffffffUL,
wchan,
0UL,
0UL,
task->exit_signal,
task_cpu(task),
task->rt_priority,
task->policy,
(unsigned long long)delayacct_blkio_ticks(task),
cputime_to_clock_t(gtime),
cputime_to_clock_t(cgtime));
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)
{
int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0;
struct mm_struct *mm = get_task_mm(task);
if (mm) {
size = task_statm(mm, &shared, &text, &data, &resident);
mmput(mm);
}
seq_printf(m, "%d %d %d %d %d %d %d\n",
size, resident, shared, text, lib, data, 0);
return 0;
}