linux/fs/coredump.c

854 lines
21 KiB
C
Raw Normal View History

#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/freezer.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/perf_event.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/coredump.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
#include <linux/tracehook.h>
#include <linux/kmod.h>
#include <linux/fsnotify.h>
#include <linux/fs_struct.h>
#include <linux/pipe_fs_i.h>
#include <linux/oom.h>
#include <linux/compat.h>
2016-03-22 21:25:36 +00:00
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/path.h>
#include <linux/timekeeping.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>
#include <asm/exec.h>
#include <trace/events/task.h>
#include "internal.h"
#include <trace/events/sched.h>
int core_uses_pid;
unsigned int core_pipe_limit;
char core_pattern[CORENAME_MAX_SIZE] = "core";
static int core_name_size = CORENAME_MAX_SIZE;
struct core_name {
char *corename;
int used, size;
};
/* The maximal length of core_pattern is also specified in sysctl.c */
static int expand_corename(struct core_name *cn, int size)
{
char *corename = krealloc(cn->corename, size, GFP_KERNEL);
if (!corename)
return -ENOMEM;
if (size > core_name_size) /* racy but harmless */
core_name_size = size;
cn->size = ksize(corename);
cn->corename = corename;
return 0;
}
static __printf(2, 0) int cn_vprintf(struct core_name *cn, const char *fmt,
va_list arg)
{
int free, need;
coredump: fix va_list corruption A va_list needs to be copied in case it needs to be used twice. Thanks to Hugh for debugging this issue, leading to various panics. Tested: lpq84:~# echo "|/foobar12345 %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h" >/proc/sys/kernel/core_pattern 'produce_core' is simply : main() { *(int *)0 = 1;} lpq84:~# ./produce_core Segmentation fault (core dumped) lpq84:~# dmesg | tail -1 [ 614.352947] Core dump to |/foobar12345 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 (null) pipe failed Notice the last argument was replaced by a NULL (we were lucky enough to not crash, but do not try this on your production machine !) After fix : lpq83:~# echo "|/foobar12345 %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h" >/proc/sys/kernel/core_pattern lpq83:~# ./produce_core Segmentation fault lpq83:~# dmesg | tail -1 [ 740.800441] Core dump to |/foobar12345 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 pipe failed Fixes: 5fe9d8ca21cc ("coredump: cn_vprintf() has no reason to call vsnprintf() twice") Signed-off-by: Eric Dumazet <edumazet@google.com> Diagnosed-by: Hugh Dickins <hughd@google.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: stable@vger.kernel.org # 3.11+ Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-19 17:15:07 +00:00
va_list arg_copy;
again:
free = cn->size - cn->used;
coredump: fix va_list corruption A va_list needs to be copied in case it needs to be used twice. Thanks to Hugh for debugging this issue, leading to various panics. Tested: lpq84:~# echo "|/foobar12345 %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h" >/proc/sys/kernel/core_pattern 'produce_core' is simply : main() { *(int *)0 = 1;} lpq84:~# ./produce_core Segmentation fault (core dumped) lpq84:~# dmesg | tail -1 [ 614.352947] Core dump to |/foobar12345 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 lpq84 (null) pipe failed Notice the last argument was replaced by a NULL (we were lucky enough to not crash, but do not try this on your production machine !) After fix : lpq83:~# echo "|/foobar12345 %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h %h" >/proc/sys/kernel/core_pattern lpq83:~# ./produce_core Segmentation fault lpq83:~# dmesg | tail -1 [ 740.800441] Core dump to |/foobar12345 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 lpq83 pipe failed Fixes: 5fe9d8ca21cc ("coredump: cn_vprintf() has no reason to call vsnprintf() twice") Signed-off-by: Eric Dumazet <edumazet@google.com> Diagnosed-by: Hugh Dickins <hughd@google.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: stable@vger.kernel.org # 3.11+ Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-19 17:15:07 +00:00
va_copy(arg_copy, arg);
need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy);
va_end(arg_copy);
if (need < free) {
cn->used += need;
return 0;
}
if (!expand_corename(cn, cn->size + need - free + 1))
goto again;
return -ENOMEM;
}
static __printf(2, 3) int cn_printf(struct core_name *cn, const char *fmt, ...)
{
va_list arg;
int ret;
va_start(arg, fmt);
ret = cn_vprintf(cn, fmt, arg);
va_end(arg);
return ret;
}
static __printf(2, 3)
int cn_esc_printf(struct core_name *cn, const char *fmt, ...)
{
int cur = cn->used;
va_list arg;
int ret;
va_start(arg, fmt);
ret = cn_vprintf(cn, fmt, arg);
va_end(arg);
if (ret == 0) {
/*
* Ensure that this coredump name component can't cause the
* resulting corefile path to consist of a ".." or ".".
*/
if ((cn->used - cur == 1 && cn->corename[cur] == '.') ||
(cn->used - cur == 2 && cn->corename[cur] == '.'
&& cn->corename[cur+1] == '.'))
cn->corename[cur] = '!';
/*
* Empty names are fishy and could be used to create a "//" in a
* corefile name, causing the coredump to happen one directory
* level too high. Enforce that all components of the core
* pattern are at least one character long.
*/
if (cn->used == cur)
ret = cn_printf(cn, "!");
}
for (; cur < cn->used; ++cur) {
if (cn->corename[cur] == '/')
cn->corename[cur] = '!';
}
return ret;
}
static int cn_print_exe_file(struct core_name *cn)
{
struct file *exe_file;
char *pathbuf, *path;
int ret;
exe_file = get_mm_exe_file(current->mm);
if (!exe_file)
return cn_esc_printf(cn, "%s (path unknown)", current->comm);
pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
if (!pathbuf) {
ret = -ENOMEM;
goto put_exe_file;
}
path = file_path(exe_file, pathbuf, PATH_MAX);
if (IS_ERR(path)) {
ret = PTR_ERR(path);
goto free_buf;
}
ret = cn_esc_printf(cn, "%s", path);
free_buf:
kfree(pathbuf);
put_exe_file:
fput(exe_file);
return ret;
}
/* format_corename will inspect the pattern parameter, and output a
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
*/
static int format_corename(struct core_name *cn, struct coredump_params *cprm)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
int pid_in_pattern = 0;
int err = 0;
cn->used = 0;
cn->corename = NULL;
if (expand_corename(cn, core_name_size))
return -ENOMEM;
cn->corename[0] = '\0';
if (ispipe)
++pat_ptr;
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
if (*pat_ptr != '%') {
err = cn_printf(cn, "%c", *pat_ptr++);
} else {
switch (*++pat_ptr) {
/* single % at the end, drop that */
case 0:
goto out;
/* Double percent, output one percent */
case '%':
err = cn_printf(cn, "%c", '%');
break;
/* pid */
case 'p':
pid_in_pattern = 1;
err = cn_printf(cn, "%d",
task_tgid_vnr(current));
break;
/* global pid */
case 'P':
err = cn_printf(cn, "%d",
task_tgid_nr(current));
break;
coredump: add %i/%I in core_pattern to report the tid of the crashed thread format_corename() can only pass the leader's pid to the core handler, but there is no simple way to figure out which thread originated the coredump. As Jan explains, this also means that there is no simple way to create the backtrace of the crashed process: As programs are mostly compiled with implicit gcc -fomit-frame-pointer one needs program's .eh_frame section (equivalently PT_GNU_EH_FRAME segment) or .debug_frame section. .debug_frame usually is present only in separate debug info files usually not even installed on the system. While .eh_frame is a part of the executable/library (and it is even always mapped for C++ exceptions unwinding) it no longer has to be present anywhere on the disk as the program could be upgraded in the meantime and the running instance has its executable file already unlinked from disk. One possibility is to echo 0x3f >/proc/*/coredump_filter and dump all the file-backed memory including the executable's .eh_frame section. But that can create huge core files, for example even due to mmapped data files. Other possibility would be to read .eh_frame from /proc/PID/mem at the core_pattern handler time of the core dump. For the backtrace one needs to read the register state first which can be done from core_pattern handler: ptrace(PTRACE_SEIZE, tid, 0, PTRACE_O_TRACEEXIT) close(0); // close pipe fd to resume the sleeping dumper waitpid(); // should report EXIT PTRACE_GETREGS or other requests The remaining problem is how to get the 'tid' value of the crashed thread. It could be read from the first NT_PRSTATUS note of the core file but that makes the core_pattern handler complicated. Unfortunately %t is already used so this patch uses %i/%I. Automatic Bug Reporting Tool (https://github.com/abrt/abrt/wiki/overview) is experimenting with this. It is using the elfutils (https://fedorahosted.org/elfutils/) unwinder for generating the backtraces. Apart from not needing matching executables as mentioned above, another advantage is that we can get the backtrace without saving the core (which might be quite large) to disk. [mmilata@redhat.com: final paragraph of changelog] Signed-off-by: Jan Kratochvil <jan.kratochvil@redhat.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com> Cc: Mark Wielaard <mjw@redhat.com> Cc: Martin Milata <mmilata@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-13 22:53:35 +00:00
case 'i':
err = cn_printf(cn, "%d",
task_pid_vnr(current));
break;
case 'I':
err = cn_printf(cn, "%d",
task_pid_nr(current));
break;
/* uid */
case 'u':
err = cn_printf(cn, "%u",
from_kuid(&init_user_ns,
cred->uid));
break;
/* gid */
case 'g':
err = cn_printf(cn, "%u",
from_kgid(&init_user_ns,
cred->gid));
break;
case 'd':
err = cn_printf(cn, "%d",
__get_dumpable(cprm->mm_flags));
break;
/* signal that caused the coredump */
case 's':
err = cn_printf(cn, "%d",
cprm->siginfo->si_signo);
break;
/* UNIX time of coredump */
case 't': {
time64_t time;
time = ktime_get_real_seconds();
err = cn_printf(cn, "%lld", time);
break;
}
/* hostname */
case 'h':
down_read(&uts_sem);
err = cn_esc_printf(cn, "%s",
utsname()->nodename);
up_read(&uts_sem);
break;
/* executable */
case 'e':
err = cn_esc_printf(cn, "%s", current->comm);
break;
case 'E':
err = cn_print_exe_file(cn);
break;
/* core limit size */
case 'c':
err = cn_printf(cn, "%lu",
rlimit(RLIMIT_CORE));
break;
default:
break;
}
++pat_ptr;
}
if (err)
return err;
}
out:
/* Backward compatibility with core_uses_pid:
*
* If core_pattern does not include a %p (as is the default)
* and core_uses_pid is set, then .%pid will be appended to
* the filename. Do not do this for piped commands. */
if (!ispipe && !pid_in_pattern && core_uses_pid) {
err = cn_printf(cn, ".%d", task_tgid_vnr(current));
if (err)
return err;
}
return ispipe;
}
static int zap_process(struct task_struct *start, int exit_code, int flags)
{
struct task_struct *t;
int nr = 0;
/* ignore all signals except SIGKILL, see prepare_signal() */
start->signal->flags = SIGNAL_GROUP_COREDUMP | flags;
start->signal->group_exit_code = exit_code;
start->signal->group_stop_count = 0;
for_each_thread(start, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
if (t != current && t->mm) {
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
nr++;
}
}
return nr;
}
coredump: only SIGKILL should interrupt the coredumping task There are 2 well known and ancient problems with coredump/signals, and a lot of related bug reports: - do_coredump() clears TIF_SIGPENDING but of course this can't help if, say, SIGCHLD comes after that. In this case the coredump can fail unexpectedly. See for example wait_for_dump_helper()->signal_pending() check but there are other reasons. - At the same time, dumping a huge core on the slow media can take a lot of time/resources and there is no way to kill the coredumping task reliably. In particular this is not oom_kill-friendly. This patch tries to fix the 1st problem, and makes the preparation for the next changes. We add the new SIGNAL_GROUP_COREDUMP flag set by zap_threads() to indicate that this process dumps the core. prepare_signal() checks this flag and nacks any signal except SIGKILL. Note that this check tries to be conservative, in the long term we should probably treat the SIGNAL_GROUP_EXIT case equally but this needs more discussion. See marc.info/?l=linux-kernel&m=120508897917439 Notes: - recalc_sigpending() doesn't check SIGNAL_GROUP_COREDUMP. The patch assumes that dump_write/etc paths should never call it, but we can change it as well. - There is another source of TIF_SIGPENDING, freezer. This will be addressed separately. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Mandeep Singh Baines <msb@chromium.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:10 +00:00
static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
struct core_state *core_state, int exit_code)
{
struct task_struct *g, *p;
unsigned long flags;
int nr = -EAGAIN;
spin_lock_irq(&tsk->sighand->siglock);
if (!signal_group_exit(tsk->signal)) {
mm->core_state = core_state;
coredump: ensure that SIGKILL always kills the dumping thread prepare_signal() blesses SIGKILL sent to the dumping process but this signal can be "lost" anyway. The problems is, complete_signal() sees SIGNAL_GROUP_EXIT and skips the "kill them all" logic. And even if the dumping process is single-threaded (so the target is always "correct"), the group-wide SIGKILL is not recorded in task->pending and thus __fatal_signal_pending() won't be true. A multi-threaded case has even more problems. And even ignoring all technical details, SIGNAL_GROUP_EXIT doesn't look right to me. This coredumping process is not exiting yet, it can do a lot of work dumping the core. With this patch the dumping process doesn't have SIGNAL_GROUP_EXIT, we set signal->group_exit_task instead. This makes signal_group_exit() true and thus this should equally close the races with exit/exec/stop but allows to kill the dumping thread reliably. Notes: - It is not clear what should we do with ->group_exit_code if the dumper was killed, see the next change. - we need more (hopefully straightforward) changes to ensure that SIGKILL actually interrupts the coredump. Basically we need to check __fatal_signal_pending() in dump_write() and dump_seek(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Mandeep Singh Baines <msb@chromium.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:12 +00:00
tsk->signal->group_exit_task = tsk;
nr = zap_process(tsk, exit_code, 0);
coredump: only SIGKILL should interrupt the coredumping task There are 2 well known and ancient problems with coredump/signals, and a lot of related bug reports: - do_coredump() clears TIF_SIGPENDING but of course this can't help if, say, SIGCHLD comes after that. In this case the coredump can fail unexpectedly. See for example wait_for_dump_helper()->signal_pending() check but there are other reasons. - At the same time, dumping a huge core on the slow media can take a lot of time/resources and there is no way to kill the coredumping task reliably. In particular this is not oom_kill-friendly. This patch tries to fix the 1st problem, and makes the preparation for the next changes. We add the new SIGNAL_GROUP_COREDUMP flag set by zap_threads() to indicate that this process dumps the core. prepare_signal() checks this flag and nacks any signal except SIGKILL. Note that this check tries to be conservative, in the long term we should probably treat the SIGNAL_GROUP_EXIT case equally but this needs more discussion. See marc.info/?l=linux-kernel&m=120508897917439 Notes: - recalc_sigpending() doesn't check SIGNAL_GROUP_COREDUMP. The patch assumes that dump_write/etc paths should never call it, but we can change it as well. - There is another source of TIF_SIGPENDING, freezer. This will be addressed separately. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Mandeep Singh Baines <msb@chromium.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:10 +00:00
clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
}
spin_unlock_irq(&tsk->sighand->siglock);
if (unlikely(nr < 0))
return nr;
tsk->flags |= PF_DUMPCORE;
if (atomic_read(&mm->mm_users) == nr + 1)
goto done;
/*
* We should find and kill all tasks which use this mm, and we should
* count them correctly into ->nr_threads. We don't take tasklist
* lock, but this is safe wrt:
*
* fork:
* None of sub-threads can fork after zap_process(leader). All
* processes which were created before this point should be
* visible to zap_threads() because copy_process() adds the new
* process to the tail of init_task.tasks list, and lock/unlock
* of ->siglock provides a memory barrier.
*
* do_exit:
* The caller holds mm->mmap_sem. This means that the task which
* uses this mm can't pass exit_mm(), so it can't exit or clear
* its ->mm.
*
* de_thread:
* It does list_replace_rcu(&leader->tasks, &current->tasks),
* we must see either old or new leader, this does not matter.
* However, it can change p->sighand, so lock_task_sighand(p)
* must be used. Since p->mm != NULL and we hold ->mmap_sem
* it can't fail.
*
* Note also that "g" can be the old leader with ->mm == NULL
* and already unhashed and thus removed from ->thread_group.
* This is OK, __unhash_process()->list_del_rcu() does not
* clear the ->next pointer, we will find the new leader via
* next_thread().
*/
rcu_read_lock();
for_each_process(g) {
if (g == tsk->group_leader)
continue;
if (g->flags & PF_KTHREAD)
continue;
for_each_thread(g, p) {
if (unlikely(!p->mm))
continue;
if (unlikely(p->mm == mm)) {
lock_task_sighand(p, &flags);
nr += zap_process(p, exit_code,
SIGNAL_GROUP_EXIT);
unlock_task_sighand(p, &flags);
}
break;
}
}
rcu_read_unlock();
done:
atomic_set(&core_state->nr_threads, nr);
return nr;
}
static int coredump_wait(int exit_code, struct core_state *core_state)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
int core_waiters = -EBUSY;
init_completion(&core_state->startup);
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
if (!mm->core_state)
core_waiters = zap_threads(tsk, mm, core_state, exit_code);
up_write(&mm->mmap_sem);
if (core_waiters > 0) {
struct core_thread *ptr;
freezer_do_not_count();
wait_for_completion(&core_state->startup);
freezer_count();
/*
* Wait for all the threads to become inactive, so that
* all the thread context (extended register state, like
* fpu etc) gets copied to the memory.
*/
ptr = core_state->dumper.next;
while (ptr != NULL) {
wait_task_inactive(ptr->task, 0);
ptr = ptr->next;
}
}
return core_waiters;
}
static void coredump_finish(struct mm_struct *mm, bool core_dumped)
{
struct core_thread *curr, *next;
struct task_struct *task;
coredump: ensure that SIGKILL always kills the dumping thread prepare_signal() blesses SIGKILL sent to the dumping process but this signal can be "lost" anyway. The problems is, complete_signal() sees SIGNAL_GROUP_EXIT and skips the "kill them all" logic. And even if the dumping process is single-threaded (so the target is always "correct"), the group-wide SIGKILL is not recorded in task->pending and thus __fatal_signal_pending() won't be true. A multi-threaded case has even more problems. And even ignoring all technical details, SIGNAL_GROUP_EXIT doesn't look right to me. This coredumping process is not exiting yet, it can do a lot of work dumping the core. With this patch the dumping process doesn't have SIGNAL_GROUP_EXIT, we set signal->group_exit_task instead. This makes signal_group_exit() true and thus this should equally close the races with exit/exec/stop but allows to kill the dumping thread reliably. Notes: - It is not clear what should we do with ->group_exit_code if the dumper was killed, see the next change. - we need more (hopefully straightforward) changes to ensure that SIGKILL actually interrupts the coredump. Basically we need to check __fatal_signal_pending() in dump_write() and dump_seek(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Mandeep Singh Baines <msb@chromium.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:12 +00:00
spin_lock_irq(&current->sighand->siglock);
if (core_dumped && !__fatal_signal_pending(current))
current->signal->group_exit_code |= 0x80;
coredump: ensure that SIGKILL always kills the dumping thread prepare_signal() blesses SIGKILL sent to the dumping process but this signal can be "lost" anyway. The problems is, complete_signal() sees SIGNAL_GROUP_EXIT and skips the "kill them all" logic. And even if the dumping process is single-threaded (so the target is always "correct"), the group-wide SIGKILL is not recorded in task->pending and thus __fatal_signal_pending() won't be true. A multi-threaded case has even more problems. And even ignoring all technical details, SIGNAL_GROUP_EXIT doesn't look right to me. This coredumping process is not exiting yet, it can do a lot of work dumping the core. With this patch the dumping process doesn't have SIGNAL_GROUP_EXIT, we set signal->group_exit_task instead. This makes signal_group_exit() true and thus this should equally close the races with exit/exec/stop but allows to kill the dumping thread reliably. Notes: - It is not clear what should we do with ->group_exit_code if the dumper was killed, see the next change. - we need more (hopefully straightforward) changes to ensure that SIGKILL actually interrupts the coredump. Basically we need to check __fatal_signal_pending() in dump_write() and dump_seek(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Mandeep Singh Baines <msb@chromium.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:12 +00:00
current->signal->group_exit_task = NULL;
current->signal->flags = SIGNAL_GROUP_EXIT;
spin_unlock_irq(&current->sighand->siglock);
next = mm->core_state->dumper.next;
while ((curr = next) != NULL) {
next = curr->next;
task = curr->task;
/*
* see exit_mm(), curr->task must not see
* ->task == NULL before we read ->next.
*/
smp_mb();
curr->task = NULL;
wake_up_process(task);
}
mm->core_state = NULL;
}
coredump: introduce dump_interrupted() By discussion with Mandeep. Change dump_write(), dump_seek() and do_coredump() to check signal_pending() and abort if it is true. dump_seek() does this only before f_op->llseek(), otherwise it relies on dump_write(). We need this change to ensure that the coredump won't delay suspend, and to ensure it reacts to SIGKILL "quickly enough", a core dump can take a lot of time. In particular this can help oom-killer. We add the new trivial helper, dump_interrupted() to add the comments and to simplify the potential freezer changes. Perhaps it will have more callers. Ideally it should do try_to_freeze() but then we need the unpleasant changes in dump_write() and wait_for_dump_helpers(). It is not trivial to change dump_write() to restart if f_op->write() fails because of freezing(). We need to handle the short writes, we need to clear TIF_SIGPENDING (and we can't rely on recalc_sigpending() unless we change it to check PF_DUMPCORE). And if the buggy f_op->write() sets TIF_SIGPENDING we can not distinguish this case from the race with freeze_task() + __thaw_task(). So we simply accept the fact that the freezer can truncate a core-dump but at least you can reliably suspend. Hopefully we can tolerate this unlikely case and the necessary complications doesn't worth a trouble. But if we decide to make the coredumping freezable later we can do this on top of this change. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Mandeep Singh Baines <msb@chromium.org> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:15 +00:00
static bool dump_interrupted(void)
{
/*
* SIGKILL or freezing() interrupt the coredumping. Perhaps we
* can do try_to_freeze() and check __fatal_signal_pending(),
* but then we need to teach dump_write() to restart and clear
* TIF_SIGPENDING.
*/
return signal_pending(current);
}
static void wait_for_dump_helpers(struct file *file)
{
struct pipe_inode_info *pipe = file->private_data;
pipe_lock(pipe);
pipe->readers++;
pipe->writers--;
wake_up_interruptible_sync(&pipe->wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
pipe_unlock(pipe);
/*
* We actually want wait_event_freezable() but then we need
* to clear TIF_SIGPENDING and improve dump_interrupted().
*/
wait_event_interruptible(pipe->wait, pipe->readers == 1);
pipe_lock(pipe);
pipe->readers--;
pipe->writers++;
pipe_unlock(pipe);
}
/*
* umh_pipe_setup
* helper function to customize the process used
* to collect the core in userspace. Specifically
* it sets up a pipe and installs it as fd 0 (stdin)
* for the process. Returns 0 on success, or
* PTR_ERR on failure.
* Note that it also sets the core limit to 1. This
* is a special value that we use to trap recursive
* core dumps
*/
static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
{
struct file *files[2];
struct coredump_params *cp = (struct coredump_params *)info->data;
int err = create_pipe_files(files, 0);
if (err)
return err;
cp->file = files[1];
err = replace_fd(0, files[0], 0);
fput(files[0]);
/* and disallow core files too */
current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
return err;
}
void do_coredump(const siginfo_t *siginfo)
{
struct core_state core_state;
struct core_name cn;
struct mm_struct *mm = current->mm;
struct linux_binfmt * binfmt;
const struct cred *old_cred;
struct cred *cred;
int retval = 0;
int ispipe;
struct files_struct *displaced;
fs: if a coredump already exists, unlink and recreate with O_EXCL It was possible for an attacking user to trick root (or another user) into writing his coredumps into an attacker-readable, pre-existing file using rename() or link(), causing the disclosure of secret data from the victim process' virtual memory. Depending on the configuration, it was also possible to trick root into overwriting system files with coredumps. Fix that issue by never writing coredumps into existing files. Requirements for the attack: - The attack only applies if the victim's process has a nonzero RLIMIT_CORE and is dumpable. - The attacker can trick the victim into coredumping into an attacker-writable directory D, either because the core_pattern is relative and the victim's cwd is attacker-writable or because an absolute core_pattern pointing to a world-writable directory is used. - The attacker has one of these: A: on a system with protected_hardlinks=0: execute access to a folder containing a victim-owned, attacker-readable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (In practice, there are lots of files that fulfill this condition, e.g. entries in Debian's /var/lib/dpkg/info/.) This does not apply to most Linux systems because most distros set protected_hardlinks=1. B: on a system with protected_hardlinks=1: execute access to a folder containing a victim-owned, attacker-readable and attacker-writable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (This seems to be uncommon.) C: on any system, independent of protected_hardlinks: write access to a non-sticky folder containing a victim-owned, attacker-readable file on the same partition as D (This seems to be uncommon.) The basic idea is that the attacker moves the victim-owned file to where he expects the victim process to dump its core. The victim process dumps its core into the existing file, and the attacker reads the coredump from it. If the attacker can't move the file because he does not have write access to the containing directory, he can instead link the file to a directory he controls, then wait for the original link to the file to be deleted (because the kernel checks that the link count of the corefile is 1). A less reliable variant that requires D to be non-sticky works with link() and does not require deletion of the original link: link() the file into D, but then unlink() it directly before the kernel performs the link count check. On systems with protected_hardlinks=0, this variant allows an attacker to not only gain information from coredumps, but also clobber existing, victim-writable files with coredumps. (This could theoretically lead to a privilege escalation.) Signed-off-by: Jann Horn <jann@thejh.net> Cc: Kees Cook <keescook@chromium.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 22:38:28 +00:00
/* require nonrelative corefile path and be extra careful */
bool need_suid_safe = false;
bool core_dumped = false;
static atomic_t core_dump_count = ATOMIC_INIT(0);
struct coredump_params cprm = {
.siginfo = siginfo,
.regs = signal_pt_regs(),
.limit = rlimit(RLIMIT_CORE),
/*
* We must use the same mm->flags while dumping core to avoid
* inconsistency of bit flags, since this flag is not protected
* by any locks.
*/
.mm_flags = mm->flags,
};
audit_core_dumps(siginfo->si_signo);
binfmt = mm->binfmt;
if (!binfmt || !binfmt->core_dump)
goto fail;
if (!__get_dumpable(cprm.mm_flags))
goto fail;
cred = prepare_creds();
if (!cred)
goto fail;
/*
* We cannot trust fsuid as being the "true" uid of the process
* nor do we know its entire history. We only know it was tainted
* so we dump it as root in mode 2, and only into a controlled
* environment (pipe handler or fully qualified path).
*/
if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) {
/* Setuid core dump mode */
cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */
fs: if a coredump already exists, unlink and recreate with O_EXCL It was possible for an attacking user to trick root (or another user) into writing his coredumps into an attacker-readable, pre-existing file using rename() or link(), causing the disclosure of secret data from the victim process' virtual memory. Depending on the configuration, it was also possible to trick root into overwriting system files with coredumps. Fix that issue by never writing coredumps into existing files. Requirements for the attack: - The attack only applies if the victim's process has a nonzero RLIMIT_CORE and is dumpable. - The attacker can trick the victim into coredumping into an attacker-writable directory D, either because the core_pattern is relative and the victim's cwd is attacker-writable or because an absolute core_pattern pointing to a world-writable directory is used. - The attacker has one of these: A: on a system with protected_hardlinks=0: execute access to a folder containing a victim-owned, attacker-readable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (In practice, there are lots of files that fulfill this condition, e.g. entries in Debian's /var/lib/dpkg/info/.) This does not apply to most Linux systems because most distros set protected_hardlinks=1. B: on a system with protected_hardlinks=1: execute access to a folder containing a victim-owned, attacker-readable and attacker-writable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (This seems to be uncommon.) C: on any system, independent of protected_hardlinks: write access to a non-sticky folder containing a victim-owned, attacker-readable file on the same partition as D (This seems to be uncommon.) The basic idea is that the attacker moves the victim-owned file to where he expects the victim process to dump its core. The victim process dumps its core into the existing file, and the attacker reads the coredump from it. If the attacker can't move the file because he does not have write access to the containing directory, he can instead link the file to a directory he controls, then wait for the original link to the file to be deleted (because the kernel checks that the link count of the corefile is 1). A less reliable variant that requires D to be non-sticky works with link() and does not require deletion of the original link: link() the file into D, but then unlink() it directly before the kernel performs the link count check. On systems with protected_hardlinks=0, this variant allows an attacker to not only gain information from coredumps, but also clobber existing, victim-writable files with coredumps. (This could theoretically lead to a privilege escalation.) Signed-off-by: Jann Horn <jann@thejh.net> Cc: Kees Cook <keescook@chromium.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 22:38:28 +00:00
need_suid_safe = true;
}
retval = coredump_wait(siginfo->si_signo, &core_state);
if (retval < 0)
goto fail_creds;
old_cred = override_creds(cred);
ispipe = format_corename(&cn, &cprm);
if (ispipe) {
int dump_count;
char **helper_argv;
struct subprocess_info *sub_info;
if (ispipe < 0) {
printk(KERN_WARNING "format_corename failed\n");
printk(KERN_WARNING "Aborting core\n");
goto fail_unlock;
}
if (cprm.limit == 1) {
/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
*
* Normally core limits are irrelevant to pipes, since
* we're not writing to the file system, but we use
* cprm.limit of 1 here as a special value, this is a
* consistent way to catch recursive crashes.
* We can still crash if the core_pattern binary sets
* RLIM_CORE = !1, but it runs as root, and can do
* lots of stupid things.
*
* Note that we use task_tgid_vnr here to grab the pid
* of the process group leader. That way we get the
* right pid if a thread in a multi-threaded
* core_pattern process dies.
*/
printk(KERN_WARNING
"Process %d(%s) has RLIMIT_CORE set to 1\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Aborting core\n");
goto fail_unlock;
}
cprm.limit = RLIM_INFINITY;
dump_count = atomic_inc_return(&core_dump_count);
if (core_pipe_limit && (core_pipe_limit < dump_count)) {
printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Skipping core dump\n");
goto fail_dropcount;
}
helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL);
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
goto fail_dropcount;
}
retval = -ENOMEM;
sub_info = call_usermodehelper_setup(helper_argv[0],
helper_argv, NULL, GFP_KERNEL,
umh_pipe_setup, NULL, &cprm);
if (sub_info)
retval = call_usermodehelper_exec(sub_info,
UMH_WAIT_EXEC);
argv_free(helper_argv);
if (retval) {
printk(KERN_INFO "Core dump to |%s pipe failed\n",
cn.corename);
goto close_fail;
}
} else {
struct inode *inode;
2016-03-22 21:25:36 +00:00
int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
O_LARGEFILE | O_EXCL;
if (cprm.limit < binfmt->min_coredump)
goto fail_unlock;
fs: if a coredump already exists, unlink and recreate with O_EXCL It was possible for an attacking user to trick root (or another user) into writing his coredumps into an attacker-readable, pre-existing file using rename() or link(), causing the disclosure of secret data from the victim process' virtual memory. Depending on the configuration, it was also possible to trick root into overwriting system files with coredumps. Fix that issue by never writing coredumps into existing files. Requirements for the attack: - The attack only applies if the victim's process has a nonzero RLIMIT_CORE and is dumpable. - The attacker can trick the victim into coredumping into an attacker-writable directory D, either because the core_pattern is relative and the victim's cwd is attacker-writable or because an absolute core_pattern pointing to a world-writable directory is used. - The attacker has one of these: A: on a system with protected_hardlinks=0: execute access to a folder containing a victim-owned, attacker-readable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (In practice, there are lots of files that fulfill this condition, e.g. entries in Debian's /var/lib/dpkg/info/.) This does not apply to most Linux systems because most distros set protected_hardlinks=1. B: on a system with protected_hardlinks=1: execute access to a folder containing a victim-owned, attacker-readable and attacker-writable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (This seems to be uncommon.) C: on any system, independent of protected_hardlinks: write access to a non-sticky folder containing a victim-owned, attacker-readable file on the same partition as D (This seems to be uncommon.) The basic idea is that the attacker moves the victim-owned file to where he expects the victim process to dump its core. The victim process dumps its core into the existing file, and the attacker reads the coredump from it. If the attacker can't move the file because he does not have write access to the containing directory, he can instead link the file to a directory he controls, then wait for the original link to the file to be deleted (because the kernel checks that the link count of the corefile is 1). A less reliable variant that requires D to be non-sticky works with link() and does not require deletion of the original link: link() the file into D, but then unlink() it directly before the kernel performs the link count check. On systems with protected_hardlinks=0, this variant allows an attacker to not only gain information from coredumps, but also clobber existing, victim-writable files with coredumps. (This could theoretically lead to a privilege escalation.) Signed-off-by: Jann Horn <jann@thejh.net> Cc: Kees Cook <keescook@chromium.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 22:38:28 +00:00
if (need_suid_safe && cn.corename[0] != '/') {
printk(KERN_WARNING "Pid %d(%s) can only dump core "\
"to fully qualified path!\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Skipping core dump\n");
goto fail_unlock;
}
fs: if a coredump already exists, unlink and recreate with O_EXCL It was possible for an attacking user to trick root (or another user) into writing his coredumps into an attacker-readable, pre-existing file using rename() or link(), causing the disclosure of secret data from the victim process' virtual memory. Depending on the configuration, it was also possible to trick root into overwriting system files with coredumps. Fix that issue by never writing coredumps into existing files. Requirements for the attack: - The attack only applies if the victim's process has a nonzero RLIMIT_CORE and is dumpable. - The attacker can trick the victim into coredumping into an attacker-writable directory D, either because the core_pattern is relative and the victim's cwd is attacker-writable or because an absolute core_pattern pointing to a world-writable directory is used. - The attacker has one of these: A: on a system with protected_hardlinks=0: execute access to a folder containing a victim-owned, attacker-readable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (In practice, there are lots of files that fulfill this condition, e.g. entries in Debian's /var/lib/dpkg/info/.) This does not apply to most Linux systems because most distros set protected_hardlinks=1. B: on a system with protected_hardlinks=1: execute access to a folder containing a victim-owned, attacker-readable and attacker-writable file on the same partition as D, and the victim-owned file will be deleted before the main part of the attack takes place. (This seems to be uncommon.) C: on any system, independent of protected_hardlinks: write access to a non-sticky folder containing a victim-owned, attacker-readable file on the same partition as D (This seems to be uncommon.) The basic idea is that the attacker moves the victim-owned file to where he expects the victim process to dump its core. The victim process dumps its core into the existing file, and the attacker reads the coredump from it. If the attacker can't move the file because he does not have write access to the containing directory, he can instead link the file to a directory he controls, then wait for the original link to the file to be deleted (because the kernel checks that the link count of the corefile is 1). A less reliable variant that requires D to be non-sticky works with link() and does not require deletion of the original link: link() the file into D, but then unlink() it directly before the kernel performs the link count check. On systems with protected_hardlinks=0, this variant allows an attacker to not only gain information from coredumps, but also clobber existing, victim-writable files with coredumps. (This could theoretically lead to a privilege escalation.) Signed-off-by: Jann Horn <jann@thejh.net> Cc: Kees Cook <keescook@chromium.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 22:38:28 +00:00
/*
* Unlink the file if it exists unless this is a SUID
* binary - in that case, we're running around with root
* privs and don't want to unlink another user's coredump.
*/
if (!need_suid_safe) {
mm_segment_t old_fs;
old_fs = get_fs();
set_fs(KERNEL_DS);
/*
* If it doesn't exist, that's fine. If there's some
* other problem, we'll catch it at the filp_open().
*/
(void) sys_unlink((const char __user *)cn.corename);
set_fs(old_fs);
}
/*
* There is a race between unlinking and creating the
* file, but if that causes an EEXIST here, that's
* fine - another process raced with us while creating
* the corefile, and the other process won. To userspace,
* what matters is that at least one of the two processes
* writes its coredump successfully, not which one.
*/
2016-03-22 21:25:36 +00:00
if (need_suid_safe) {
/*
* Using user namespaces, normal user tasks can change
* their current->fs->root to point to arbitrary
* directories. Since the intention of the "only dump
* with a fully qualified path" rule is to control where
* coredumps may be placed using root privileges,
* current->fs->root must not be used. Instead, use the
* root directory of init_task.
*/
struct path root;
task_lock(&init_task);
get_fs_root(init_task.fs, &root);
task_unlock(&init_task);
cprm.file = file_open_root(root.dentry, root.mnt,
cn.corename, open_flags, 0600);
path_put(&root);
} else {
cprm.file = filp_open(cn.corename, open_flags, 0600);
}
if (IS_ERR(cprm.file))
goto fail_unlock;
inode = file_inode(cprm.file);
if (inode->i_nlink > 1)
goto close_fail;
if (d_unhashed(cprm.file->f_path.dentry))
goto close_fail;
/*
* AK: actually i see no reason to not allow this for named
* pipes etc, but keep the previous behaviour for now.
*/
if (!S_ISREG(inode->i_mode))
goto close_fail;
/*
* Don't dump core if the filesystem changed owner or mode
* of the file during file creation. This is an issue when
* a process dumps core while its cwd is e.g. on a vfat
* filesystem.
*/
if (!uid_eq(inode->i_uid, current_fsuid()))
goto close_fail;
if ((inode->i_mode & 0677) != 0600)
goto close_fail;
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
goto close_fail;
}
/* get us an unshared descriptor table; almost always a no-op */
retval = unshare_files(&displaced);
if (retval)
goto close_fail;
if (displaced)
put_files_struct(displaced);
if (!dump_interrupted()) {
file_start_write(cprm.file);
core_dumped = binfmt->core_dump(&cprm);
file_end_write(cprm.file);
}
if (ispipe && core_pipe_limit)
wait_for_dump_helpers(cprm.file);
close_fail:
if (cprm.file)
filp_close(cprm.file, NULL);
fail_dropcount:
if (ispipe)
atomic_dec(&core_dump_count);
fail_unlock:
kfree(cn.corename);
coredump_finish(mm, core_dumped);
revert_creds(old_cred);
fail_creds:
put_cred(cred);
fail:
return;
}
/*
* Core dumping helper functions. These are the only things you should
* do on a core-file: use only these functions to write out all the
* necessary info.
*/
int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
{
struct file *file = cprm->file;
loff_t pos = file->f_pos;
ssize_t n;
if (cprm->written + nr > cprm->limit)
return 0;
while (nr) {
if (dump_interrupted())
return 0;
n = __kernel_write(file, addr, nr, &pos);
if (n <= 0)
return 0;
file->f_pos = pos;
cprm->written += n;
cprm->pos += n;
nr -= n;
}
return 1;
}
EXPORT_SYMBOL(dump_emit);
int dump_skip(struct coredump_params *cprm, size_t nr)
{
static char zeroes[PAGE_SIZE];
struct file *file = cprm->file;
if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
coredump: introduce dump_interrupted() By discussion with Mandeep. Change dump_write(), dump_seek() and do_coredump() to check signal_pending() and abort if it is true. dump_seek() does this only before f_op->llseek(), otherwise it relies on dump_write(). We need this change to ensure that the coredump won't delay suspend, and to ensure it reacts to SIGKILL "quickly enough", a core dump can take a lot of time. In particular this can help oom-killer. We add the new trivial helper, dump_interrupted() to add the comments and to simplify the potential freezer changes. Perhaps it will have more callers. Ideally it should do try_to_freeze() but then we need the unpleasant changes in dump_write() and wait_for_dump_helpers(). It is not trivial to change dump_write() to restart if f_op->write() fails because of freezing(). We need to handle the short writes, we need to clear TIF_SIGPENDING (and we can't rely on recalc_sigpending() unless we change it to check PF_DUMPCORE). And if the buggy f_op->write() sets TIF_SIGPENDING we can not distinguish this case from the race with freeze_task() + __thaw_task(). So we simply accept the fact that the freezer can truncate a core-dump but at least you can reliably suspend. Hopefully we can tolerate this unlikely case and the necessary complications doesn't worth a trouble. But if we decide to make the coredumping freezable later we can do this on top of this change. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Mandeep Singh Baines <msb@chromium.org> Cc: Neil Horman <nhorman@redhat.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:28:15 +00:00
if (dump_interrupted() ||
file->f_op->llseek(file, nr, SEEK_CUR) < 0)
return 0;
cprm->pos += nr;
return 1;
} else {
while (nr > PAGE_SIZE) {
if (!dump_emit(cprm, zeroes, PAGE_SIZE))
return 0;
nr -= PAGE_SIZE;
}
return dump_emit(cprm, zeroes, nr);
}
}
EXPORT_SYMBOL(dump_skip);
int dump_align(struct coredump_params *cprm, int align)
{
unsigned mod = cprm->pos & (align - 1);
if (align & (align - 1))
return 0;
return mod ? dump_skip(cprm, align - mod) : 1;
}
EXPORT_SYMBOL(dump_align);
/*
* Ensures that file size is big enough to contain the current file
* postion. This prevents gdb from complaining about a truncated file
* if the last "write" to the file was dump_skip.
*/
void dump_truncate(struct coredump_params *cprm)
{
struct file *file = cprm->file;
loff_t offset;
if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
offset = file->f_op->llseek(file, 0, SEEK_CUR);
if (i_size_read(file->f_mapping->host) < offset)
do_truncate(file->f_path.dentry, offset, 0, file);
}
}
EXPORT_SYMBOL(dump_truncate);