oom: make sure that TIF_MEMDIE is set under task_lock
OOM killer tries to exclude tasks which do not have mm_struct associated because killing such a task wouldn't help much. The OOM victim gets TIF_MEMDIE set to disable OOM killer while the current victim releases the memory and then enables the OOM killer again by dropping the flag. oom_kill_process is currently prone to a race condition when the OOM victim is already exiting and TIF_MEMDIE is set after the task releases its address space. This might theoretically lead to OOM livelock if the OOM victim blocks on an allocation later during exiting because it wouldn't kill any other process and the exiting one won't be able to exit. The situation is highly unlikely because the OOM victim is expected to release some memory which should help to sort out OOM situation. Fix this by checking task->mm and setting TIF_MEMDIE flag under task_lock which will serialize the OOM killer with exit_mm which sets task->mm to NULL. Setting the flag for current is not necessary because check and set is not racy. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
d7a94e7e11
commit
83363b917a
|
@ -438,11 +438,14 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
|
||||||
* If the task is already exiting, don't alarm the sysadmin or kill
|
* If the task is already exiting, don't alarm the sysadmin or kill
|
||||||
* its children or threads, just set TIF_MEMDIE so it can die quickly
|
* its children or threads, just set TIF_MEMDIE so it can die quickly
|
||||||
*/
|
*/
|
||||||
if (task_will_free_mem(p)) {
|
task_lock(p);
|
||||||
|
if (p->mm && task_will_free_mem(p)) {
|
||||||
set_tsk_thread_flag(p, TIF_MEMDIE);
|
set_tsk_thread_flag(p, TIF_MEMDIE);
|
||||||
|
task_unlock(p);
|
||||||
put_task_struct(p);
|
put_task_struct(p);
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
task_unlock(p);
|
||||||
|
|
||||||
if (__ratelimit(&oom_rs))
|
if (__ratelimit(&oom_rs))
|
||||||
dump_header(p, gfp_mask, order, memcg, nodemask);
|
dump_header(p, gfp_mask, order, memcg, nodemask);
|
||||||
|
@ -492,6 +495,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
|
||||||
|
|
||||||
/* mm cannot safely be dereferenced after task_unlock(victim) */
|
/* mm cannot safely be dereferenced after task_unlock(victim) */
|
||||||
mm = victim->mm;
|
mm = victim->mm;
|
||||||
|
set_tsk_thread_flag(victim, TIF_MEMDIE);
|
||||||
pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
|
pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
|
||||||
task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
|
task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
|
||||||
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
|
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
|
||||||
|
@ -522,7 +526,6 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
|
||||||
}
|
}
|
||||||
rcu_read_unlock();
|
rcu_read_unlock();
|
||||||
|
|
||||||
set_tsk_thread_flag(victim, TIF_MEMDIE);
|
|
||||||
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
|
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
|
||||||
put_task_struct(victim);
|
put_task_struct(victim);
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue