From a373966d1f64c04ba9d0159087f0fa1b5aac4c33 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Jul 2016 15:45:01 -0700 Subject: mm, oom: hide mm which is shared with kthread or global init The only case where the oom_reaper is not triggered for the oom victim is when it shares the memory with a kernel thread (aka use_mm) or with the global init. After "mm, oom: skip vforked tasks from being selected" the victim cannot be a vforked task of the global init so we are left with clone(CLONE_VM) (without CLONE_SIGHAND). use_mm() users are quite rare as well. In order to help forward progress for the OOM killer, make sure that this really rare case will not get in the way - we do this by hiding the mm from the oom killer by setting MMF_OOM_REAPED flag for it. oom_scan_process_thread will ignore any TIF_MEMDIE task if it has MMF_OOM_REAPED flag set to catch these oom victims. After this patch we should guarantee forward progress for the OOM killer even when the selected victim is sharing memory with a kernel thread or global init as long as the victims mm is still alive. Link: http://lkml.kernel.org/r/1466426628-15074-11-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Vladimir Davydov Cc: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'mm/oom_kill.c') diff --git a/mm/oom_kill.c b/mm/oom_kill.c index bfddc93ccd34..4c21f744daa6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -283,10 +283,22 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, /* * This task already has access to memory reserves and is being killed. - * Don't allow any other task to have access to the reserves. + * Don't allow any other task to have access to the reserves unless + * the task has MMF_OOM_REAPED because chances that it would release + * any memory is quite low. */ - if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) - return OOM_SCAN_ABORT; + if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) { + struct task_struct *p = find_lock_task_mm(task); + enum oom_scan_t ret = OOM_SCAN_ABORT; + + if (p) { + if (test_bit(MMF_OOM_REAPED, &p->mm->flags)) + ret = OOM_SCAN_CONTINUE; + task_unlock(p); + } + + return ret; + } /* * If task is allocating a lot of memory and has been marked to be @@ -913,9 +925,14 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, /* * We cannot use oom_reaper for the mm shared by this * process because it wouldn't get killed and so the - * memory might be still used. + * memory might be still used. Hide the mm from the oom + * killer to guarantee OOM forward progress. */ can_oom_reap = false; + set_bit(MMF_OOM_REAPED, &mm->flags); + pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n", + task_pid_nr(victim), victim->comm, + task_pid_nr(p), p->comm); continue; } do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); -- cgit v1.2.3-55-g7522