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 <rientjes@google.com>
Reported-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Ying Han <yinghan@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 18 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index b0d8943bc9fd..2b97e8f04607 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(&current->mm->oom_disable_count);
-                else if (old_val == OOM_SCORE_ADJ_MIN)
-                        atomic_dec(&current->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;
@@ -173,16 +167,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
                 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(&current->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