From c9f01245b6a7d77d17deaa71af10f6aca14fa24e Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 31 Oct 2011 17:07:15 -0700 Subject: oom: remove oom_disable_count This removes mm->oom_disable_count entirely since it's unnecessary and currently buggy. The counter was intended to be per-process but it's currently decremented in the exit path for each thread that exits, causing it to underflow. The count was originally intended to prevent oom killing threads that share memory with threads that cannot be killed since it doesn't lead to future memory freeing. The counter could be fixed to represent all threads sharing the same mm, but it's better to remove the count since: - it is possible that the OOM_DISABLE thread sharing memory with the victim is waiting on that thread to exit and will actually cause future memory freeing, and - there is no guarantee that a thread is disabled from oom killing just because another thread sharing its mm is oom disabled. Signed-off-by: David Rientjes Reported-by: Oleg Nesterov Reviewed-by: Oleg Nesterov Cc: Ying Han Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 23 +++++------------------ 1 file changed, 5 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b0d8943bc9f..2b97e8f0460 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -54,13 +54,7 @@ int test_set_oom_score_adj(int new_val) spin_lock_irq(&sighand->siglock); old_val = current->signal->oom_score_adj; - if (new_val != old_val) { - if (new_val == OOM_SCORE_ADJ_MIN) - atomic_inc(¤t->mm->oom_disable_count); - else if (old_val == OOM_SCORE_ADJ_MIN) - atomic_dec(¤t->mm->oom_disable_count); - current->signal->oom_score_adj = new_val; - } + current->signal->oom_score_adj = new_val; spin_unlock_irq(&sighand->siglock); return old_val; @@ -172,16 +166,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, if (!p) return 0; - /* - * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN - * so the entire heuristic doesn't need to be executed for something - * that cannot be killed. - */ - if (atomic_read(&p->mm->oom_disable_count)) { - task_unlock(p); - return 0; - } - /* * The memory controller may have a limit of 0 bytes, so avoid a divide * by zero, if necessary. @@ -451,6 +435,9 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) for_each_process(q) if (q->mm == mm && !same_thread_group(q, p) && !(q->flags & PF_KTHREAD)) { + if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + continue; + task_lock(q); /* Protect ->comm from prctl() */ pr_err("Kill process %d (%s) sharing same memory\n", task_pid_nr(q), q->comm); @@ -727,7 +714,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, read_lock(&tasklist_lock); if (sysctl_oom_kill_allocating_task && !oom_unkillable_task(current, NULL, nodemask) && - current->mm && !atomic_read(¤t->mm->oom_disable_count)) { + current->mm) { /* * oom_kill_process() needs tasklist_lock held. If it returns * non-zero, current could not be killed so we must fallback to -- cgit v1.2.3-18-g5258