oom: don't assume that a coredumping thread will exit soon

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.  The SIGNAL_GROUP_COREDUMP check is obviously racy, a task can
participate in coredump after it was already observed in PF_EXITING state,
so TIF_MEMDIE (which also blocks oom-killer) still can be wrongly set.
fatal_signal_pending() can be true because of SIGNAL_GROUP_COREDUMP so
out_of_memory() and mem_cgroup_out_of_memory() shouldn't blindly trust it.
 And even the name/usage of the new helper is confusing, an exiting thread
can only free its ->mm if it is the only/last task in thread group.

[akpm@linux-foundation.org: add comment]
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/oom.h

@@ -92,6 +92,17 @@ static inline bool oom_gfp_allowed(gfp_t gfp_mask)
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
+static inline bool task_will_free_mem(struct task_struct *task)
+{
+	/*
+	 * A coredumping process may sleep for an extended period in exit_mm(),
+	 * so the oom killer cannot assume that the process will promptly exit
+	 * and release memory.
+	 */
+	return (task->flags & PF_EXITING) &&
+		!(task->signal->flags & SIGNAL_GROUP_COREDUMP);
+}
+
 /* sysctls */
 extern int sysctl_oom_dump_tasks;
 extern int sysctl_oom_kill_allocating_task;

mm/memcontrol.c

@@ -1559,7 +1559,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, 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;
 	}

mm/oom_kill.c

@@ -281,7 +281,7 @@ 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 +443,7 @@ 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 +649,7 @@ 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;
 	}