OpenCloudOS-Kernel/fs/proc/array.c

719 lines
19 KiB
C
Raw Normal View History

/*
* 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;
size_t size;
char tcomm[sizeof(p->comm)];
int ret;
get_task_comm(tcomm, p);
seq_puts(m, "Name:\t");
size = seq_get_buf(m, &buf);
ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
seq_commit(m, ret < size ? ret : -1);
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;
procfs: treat parked tasks as sleeping for task state Allowing watchdog threads to be parked means that we now have the opportunity of actually seeing persistent parked threads in the output of /proc/<pid>/stat and /proc/<pid>/status. The existing code reported such threads as "Running", which is kind-of true if you think of the case where we park them as part of taking cpus offline. But if we allow parking them indefinitely, "Running" is pretty misleading, so we report them as "Sleeping" instead. We could simply report them with a new string, "Parked", but it feels like it's a bit risky for userspace to see unexpected new values; the output is already documented in Documentation/filesystems/proc.txt, and it seems like a mistake to change that lightly. The scheduler does report parked tasks with a "P" in debugging output from sched_show_task() or dump_cpu_task(), but that's a different API. Similarly, the trace_ctxwake_* routines report a "P" for parked tasks, but again, different API. This change seemed slightly cleaner than updating the task_state_array to have additional rows. TASK_DEAD should be subsumed by the exit_state bits; TASK_WAKEKILL is just a modifier; and TASK_WAKING can very reasonably be reported as "Running" (as it is now). Only TASK_PARKED shows up with unreasonable output here. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:48 +08:00
/*
* 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: Fix get_task_cred() and task_state() to not resurrect dead credentials It's possible for get_task_cred() as it currently stands to 'corrupt' a set of credentials by incrementing their usage count after their replacement by the task being accessed. What happens is that get_task_cred() can race with commit_creds(): TASK_1 TASK_2 RCU_CLEANER -->get_task_cred(TASK_2) rcu_read_lock() __cred = __task_cred(TASK_2) -->commit_creds() old_cred = TASK_2->real_cred TASK_2->real_cred = ... put_cred(old_cred) call_rcu(old_cred) [__cred->usage == 0] get_cred(__cred) [__cred->usage == 1] rcu_read_unlock() -->put_cred_rcu() [__cred->usage == 1] panic() However, since a tasks credentials are generally not changed very often, we can reasonably make use of a loop involving reading the creds pointer and using atomic_inc_not_zero() to attempt to increment it if it hasn't already hit zero. If successful, we can safely return the credentials in the knowledge that, even if the task we're accessing has released them, they haven't gone to the RCU cleanup code. We then change task_state() in procfs to use get_task_cred() rather than calling get_cred() on the result of __task_cred(), as that suffers from the same problem. Without this change, a BUG_ON in __put_cred() or in put_cred_rcu() can be tripped when it is noticed that the usage count is not zero as it ought to be, for example: kernel BUG at kernel/cred.c:168! invalid opcode: 0000 [#1] SMP last sysfs file: /sys/kernel/mm/ksm/run CPU 0 Pid: 2436, comm: master Not tainted 2.6.33.3-85.fc13.x86_64 #1 0HR330/OptiPlex 745 RIP: 0010:[<ffffffff81069881>] [<ffffffff81069881>] __put_cred+0xc/0x45 RSP: 0018:ffff88019e7e9eb8 EFLAGS: 00010202 RAX: 0000000000000001 RBX: ffff880161514480 RCX: 00000000ffffffff RDX: 00000000ffffffff RSI: ffff880140c690c0 RDI: ffff880140c690c0 RBP: ffff88019e7e9eb8 R08: 00000000000000d0 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000040 R12: ffff880140c690c0 R13: ffff88019e77aea0 R14: 00007fff336b0a5c R15: 0000000000000001 FS: 00007f12f50d97c0(0000) GS:ffff880007400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f8f461bc000 CR3: 00000001b26ce000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process master (pid: 2436, threadinfo ffff88019e7e8000, task ffff88019e77aea0) Stack: ffff88019e7e9ec8 ffffffff810698cd ffff88019e7e9ef8 ffffffff81069b45 <0> ffff880161514180 ffff880161514480 ffff880161514180 0000000000000000 <0> ffff88019e7e9f28 ffffffff8106aace 0000000000000001 0000000000000246 Call Trace: [<ffffffff810698cd>] put_cred+0x13/0x15 [<ffffffff81069b45>] commit_creds+0x16b/0x175 [<ffffffff8106aace>] set_current_groups+0x47/0x4e [<ffffffff8106ac89>] sys_setgroups+0xf6/0x105 [<ffffffff81009b02>] system_call_fastpath+0x16/0x1b Code: 48 8d 71 ff e8 7e 4e 15 00 85 c0 78 0b 8b 75 ec 48 89 df e8 ef 4a 15 00 48 83 c4 18 5b c9 c3 55 8b 07 8b 07 48 89 e5 85 c0 74 04 <0f> 0b eb fe 65 48 8b 04 25 00 cc 00 00 48 3b b8 58 04 00 00 75 RIP [<ffffffff81069881>] __put_cred+0xc/0x45 RSP <ffff88019e7e9eb8> ---[ end trace df391256a100ebdd ]--- Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-07-29 19:45:49 +08:00
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",
CAPABILITIES: remove undefined caps from all processes This is effectively a revert of 7b9a7ec565505699f503b4fcf61500dceb36e744 plus fixing it a different way... We found, when trying to run an application from an application which had dropped privs that the kernel does security checks on undefined capability bits. This was ESPECIALLY difficult to debug as those undefined bits are hidden from /proc/$PID/status. Consider a root application which drops all capabilities from ALL 4 capability sets. We assume, since the application is going to set eff/perm/inh from an array that it will clear not only the defined caps less than CAP_LAST_CAP, but also the higher 28ish bits which are undefined future capabilities. The BSET gets cleared differently. Instead it is cleared one bit at a time. The problem here is that in security/commoncap.c::cap_task_prctl() we actually check the validity of a capability being read. So any task which attempts to 'read all things set in bset' followed by 'unset all things set in bset' will not even attempt to unset the undefined bits higher than CAP_LAST_CAP. So the 'parent' will look something like: CapInh: 0000000000000000 CapPrm: 0000000000000000 CapEff: 0000000000000000 CapBnd: ffffffc000000000 All of this 'should' be fine. Given that these are undefined bits that aren't supposed to have anything to do with permissions. But they do... So lets now consider a task which cleared the eff/perm/inh completely and cleared all of the valid caps in the bset (but not the invalid caps it couldn't read out of the kernel). We know that this is exactly what the libcap-ng library does and what the go capabilities library does. They both leave you in that above situation if you try to clear all of you capapabilities from all 4 sets. If that root task calls execve() the child task will pick up all caps not blocked by the bset. The bset however does not block bits higher than CAP_LAST_CAP. So now the child task has bits in eff which are not in the parent. These are 'meaningless' undefined bits, but still bits which the parent doesn't have. The problem is now in cred_cap_issubset() (or any operation which does a subset test) as the child, while a subset for valid cap bits, is not a subset for invalid cap bits! So now we set durring commit creds that the child is not dumpable. Given it is 'more priv' than its parent. It also means the parent cannot ptrace the child and other stupidity. The solution here: 1) stop hiding capability bits in status This makes debugging easier! 2) stop giving any task undefined capability bits. it's simple, it you don't put those invalid bits in CAP_FULL_SET you won't get them in init and you won't get them in any other task either. This fixes the cap_issubset() tests and resulting fallout (which made the init task in a docker container untraceable among other things) 3) mask out undefined bits when sys_capset() is called as it might use ~0, ~0 to denote 'all capabilities' for backward/forward compatibility. This lets 'capsh --caps="all=eip" -- -c /bin/bash' run. 4) mask out undefined bit when we read a file capability off of disk as again likely all bits are set in the xattr for forward/backward compatibility. This lets 'setcap all+pe /bin/bash; /bin/bash' run Signed-off-by: Eric Paris <eparis@redhat.com> Reviewed-by: Kees Cook <keescook@chromium.org> Cc: Andrew Vagin <avagin@openvz.org> Cc: Andrew G. Morgan <morgan@kernel.org> Cc: Serge E. Hallyn <serge.hallyn@canonical.com> Cc: Kees Cook <keescook@chromium.org> Cc: Steve Grubb <sgrubb@redhat.com> Cc: Dan Walsh <dwalsh@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: James Morris <james.l.morris@oracle.com>
2014-07-24 03:36:26 +08:00
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;
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>
2015-09-05 06:42:45 +08:00
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;
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>
2015-09-05 06:42:45 +08:00
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);
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>
2015-09-05 06:42:45 +08:00
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)
{
fs/proc, core/debug: Don't expose absolute kernel addresses via wchan So the /proc/PID/stat 'wchan' field (the 30th field, which contains the absolute kernel address of the kernel function a task is blocked in) leaks absolute kernel addresses to unprivileged user-space: seq_put_decimal_ull(m, ' ', wchan); The absolute address might also leak via /proc/PID/wchan as well, if KALLSYMS is turned off or if the symbol lookup fails for some reason: static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; wchan = get_wchan(task); if (lookup_symbol_name(wchan, symname) < 0) { if (!ptrace_may_access(task, PTRACE_MODE_READ)) return 0; seq_printf(m, "%lu", wchan); } else { seq_printf(m, "%s", symname); } return 0; } This isn't ideal, because for example it trivially leaks the KASLR offset to any local attacker: fomalhaut:~> printf "%016lx\n" $(cat /proc/$$/stat | cut -d' ' -f35) ffffffff8123b380 Most real-life uses of wchan are symbolic: ps -eo pid:10,tid:10,wchan:30,comm and procps uses /proc/PID/wchan, not the absolute address in /proc/PID/stat: triton:~/tip> strace -f ps -eo pid:10,tid:10,wchan:30,comm 2>&1 | grep wchan | tail -1 open("/proc/30833/wchan", O_RDONLY) = 6 There's one compatibility quirk here: procps relies on whether the absolute value is non-zero - and we can provide that functionality by outputing "0" or "1" depending on whether the task is blocked (whether there's a wchan address). These days there appears to be very little legitimate reason user-space would be interested in the absolute address. The absolute address is mostly historic: from the days when we didn't have kallsyms and user-space procps had to do the decoding itself via the System.map. So this patch sets all numeric output to "0" or "1" and keeps only symbolic output, in /proc/PID/wchan. ( The absolute sleep address can generally still be profiled via perf, by tasks with sufficient privileges. ) Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: kasan-dev <kasan-dev@googlegroups.com> Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/20150930135917.GA3285@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-09-30 21:59:17 +08:00
unsigned long vsize, eip, esp, wchan = 0;
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);
fs/proc, core/debug: Don't expose absolute kernel addresses via wchan So the /proc/PID/stat 'wchan' field (the 30th field, which contains the absolute kernel address of the kernel function a task is blocked in) leaks absolute kernel addresses to unprivileged user-space: seq_put_decimal_ull(m, ' ', wchan); The absolute address might also leak via /proc/PID/wchan as well, if KALLSYMS is turned off or if the symbol lookup fails for some reason: static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; wchan = get_wchan(task); if (lookup_symbol_name(wchan, symname) < 0) { if (!ptrace_may_access(task, PTRACE_MODE_READ)) return 0; seq_printf(m, "%lu", wchan); } else { seq_printf(m, "%s", symname); } return 0; } This isn't ideal, because for example it trivially leaks the KASLR offset to any local attacker: fomalhaut:~> printf "%016lx\n" $(cat /proc/$$/stat | cut -d' ' -f35) ffffffff8123b380 Most real-life uses of wchan are symbolic: ps -eo pid:10,tid:10,wchan:30,comm and procps uses /proc/PID/wchan, not the absolute address in /proc/PID/stat: triton:~/tip> strace -f ps -eo pid:10,tid:10,wchan:30,comm 2>&1 | grep wchan | tail -1 open("/proc/30833/wchan", O_RDONLY) = 6 There's one compatibility quirk here: procps relies on whether the absolute value is non-zero - and we can provide that functionality by outputing "0" or "1" depending on whether the task is blocked (whether there's a wchan address). These days there appears to be very little legitimate reason user-space would be interested in the absolute address. The absolute address is mostly historic: from the days when we didn't have kallsyms and user-space procps had to do the decoding itself via the System.map. So this patch sets all numeric output to "0" or "1" and keeps only symbolic output, in /proc/PID/wchan. ( The absolute sleep address can generally still be profiled via perf, by tasks with sufficient privileges. ) Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: kasan-dev <kasan-dev@googlegroups.com> Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/20150930135917.GA3285@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-09-30 21:59:17 +08:00
/*
* We used to output the absolute kernel address, but that's an
* information leak - so instead we show a 0/1 flag here, to signal
* to user-space whether there's a wchan field in /proc/PID/wchan.
*
* This works with older implementations of procps as well.
*/
if (wchan)
seq_puts(m, " 1");
else
seq_puts(m, " 0");
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;
}
fs, proc: introduce CONFIG_PROC_CHILDREN Commit 818411616baf ("fs, proc: introduce /proc/<pid>/task/<tid>/children entry") introduced the children entry for checkpoint restore and the file is only available on kernels configured with CONFIG_EXPERT and CONFIG_CHECKPOINT_RESTORE. This is available in most distributions (Fedora, Debian, Ubuntu, CoreOS) because they usually enable CONFIG_EXPERT and CONFIG_CHECKPOINT_RESTORE. But Arch does not enable CONFIG_EXPERT or CONFIG_CHECKPOINT_RESTORE. However, the children proc file is useful outside of checkpoint restore. I would like to use it in rkt. The rkt process exec() another program it does not control, and that other program will fork()+exec() a child process. I would like to find the pid of the child process from an external tool without iterating in /proc over all processes to find which one has a parent pid equal to rkt. This commit introduces CONFIG_PROC_CHILDREN and makes CONFIG_CHECKPOINT_RESTORE select it. This allows enabling /proc/<pid>/task/<tid>/children without needing to enable CONFIG_CHECKPOINT_RESTORE and CONFIG_EXPERT. Alban tested that /proc/<pid>/task/<tid>/children is present when the kernel is configured with CONFIG_PROC_CHILDREN=y but without CONFIG_CHECKPOINT_RESTORE Signed-off-by: Iago López Galeiras <iago@endocode.com> Tested-by: Alban Crequy <alban@endocode.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Serge Hallyn <serge.hallyn@canonical.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Djalal Harouni <djalal@endocode.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:00:57 +08:00
#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,
};
fs, proc: introduce CONFIG_PROC_CHILDREN Commit 818411616baf ("fs, proc: introduce /proc/<pid>/task/<tid>/children entry") introduced the children entry for checkpoint restore and the file is only available on kernels configured with CONFIG_EXPERT and CONFIG_CHECKPOINT_RESTORE. This is available in most distributions (Fedora, Debian, Ubuntu, CoreOS) because they usually enable CONFIG_EXPERT and CONFIG_CHECKPOINT_RESTORE. But Arch does not enable CONFIG_EXPERT or CONFIG_CHECKPOINT_RESTORE. However, the children proc file is useful outside of checkpoint restore. I would like to use it in rkt. The rkt process exec() another program it does not control, and that other program will fork()+exec() a child process. I would like to find the pid of the child process from an external tool without iterating in /proc over all processes to find which one has a parent pid equal to rkt. This commit introduces CONFIG_PROC_CHILDREN and makes CONFIG_CHECKPOINT_RESTORE select it. This allows enabling /proc/<pid>/task/<tid>/children without needing to enable CONFIG_CHECKPOINT_RESTORE and CONFIG_EXPERT. Alban tested that /proc/<pid>/task/<tid>/children is present when the kernel is configured with CONFIG_PROC_CHILDREN=y but without CONFIG_CHECKPOINT_RESTORE Signed-off-by: Iago López Galeiras <iago@endocode.com> Tested-by: Alban Crequy <alban@endocode.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Serge Hallyn <serge.hallyn@canonical.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Djalal Harouni <djalal@endocode.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:00:57 +08:00
#endif /* CONFIG_PROC_CHILDREN */