oom_kill.c assumes that PF_EXITING task should exit and free the memory soon. This is wrong in many ways and one important case is the coredump. A task can sleep in exit_mm() "forever" while the coredumping sub-thread can need more memory.
Change the PF_EXITING checks to take SIGNAL_GROUP_COREDUMP into account, we add the new trivial helper for that. Note: this is only the first step, this patch doesn't try to solve other problems. For example it doesn't try to clear the wrongly set TIF_MEMDIE (SIGNAL_GROUP_COREDUMP check is obviously racy), fatal_signal_pending() can be false positive, etc. Signed-off-by: Oleg Nesterov <[email protected]> --- mm/oom_kill.c | 12 +++++++++--- 1 files changed, 9 insertions(+), 3 deletions(-) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 5340f6b..7af33b5 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -254,6 +254,12 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, } #endif +static inline bool task_will_free_mem(struct task_struct *task) +{ + return (task->flags & PF_EXITING) && + !(task->signal->flags & SIGNAL_GROUP_COREDUMP); +} + enum oom_scan_t oom_scan_process_thread(struct task_struct *task, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill) @@ -281,7 +287,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task, if (oom_task_origin(task)) return OOM_SCAN_SELECT; - if (task->flags & PF_EXITING && !force_kill) { + if (task_will_free_mem(task) && !force_kill) { /* * If this task is not being ptraced on exit, then wait for it * to finish before killing some other task unnecessarily. @@ -443,7 +449,7 @@ 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 * its children or threads, just set TIF_MEMDIE so it can die quickly */ - if (p->flags & PF_EXITING) { + if (task_will_free_mem(p)) { set_tsk_thread_flag(p, TIF_MEMDIE); put_task_struct(p); return; @@ -649,7 +655,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ - if (fatal_signal_pending(current) || current->flags & PF_EXITING) { + if (fatal_signal_pending(current) || task_will_free_mem(current)) { set_thread_flag(TIF_MEMDIE); return; } -- 1.5.5.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
