From 855b018325737f7691f9b7d86339df40aa4e47c3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:36 -0700 Subject: [PATCH] oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task Tetsuo has reported that oom_kill_allocating_task=1 will cause oom_reaper_list corruption because oom_kill_process doesn't follow standard OOM exclusion (aka ignores TIF_MEMDIE) and allows to enqueue the same task multiple times - e.g. by sacrificing the same child multiple times. This patch fixes the issue by introducing a new MMF_OOM_KILLED mm flag which is set in oom_kill_process atomically and oom reaper is disabled if the flag was already set. Signed-off-by: Michal Hocko Reported-by: Tetsuo Handa Cc: David Rientjes Cc: Mel Gorman Cc: Oleg Nesterov Cc: Hugh Dickins Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ mm/oom_kill.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 788f223f8f8f..c2d2d7c5d463 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -512,6 +512,8 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_KILLED 21 /* OOM killer has chosen this mm */ + #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) struct sighand_struct { diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f6d4ae9f1c69..1a21819a8e5e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -680,7 +680,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, unsigned int victim_points = 0; static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - bool can_oom_reap = true; + bool can_oom_reap; /* * If the task is already exiting, don't alarm the sysadmin or kill @@ -742,6 +742,10 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, /* Get a reference to safely compare mm after task_unlock(victim) */ mm = victim->mm; atomic_inc(&mm->mm_count); + + /* Make sure we do not try to oom reap the mm multiple times */ + can_oom_reap = !test_and_set_bit(MMF_OOM_KILLED, &mm->flags); + /* * We should send SIGKILL before setting TIF_MEMDIE in order to prevent * the OOM victim from depleting the memory reserves from the user -- GitLab