oom_reaper: close race with exiting task

[cascardo/linux.git] / mm / oom_kill.c

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5bb2f76..dfb1ab6 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -443,12 +443,28 @@ static bool __oom_reap_task(struct task_struct *tsk)
 {
        struct mmu_gather tlb;
        struct vm_area_struct *vma;
-       struct mm_struct *mm;
+       struct mm_struct *mm = NULL;
        struct task_struct *p;
        struct zap_details details = {.check_swap_entries = true,
                                      .ignore_dirty = true};
        bool ret = true;
 
+       /*
+        * We have to make sure to not race with the victim exit path
+        * and cause premature new oom victim selection:
+        * __oom_reap_task              exit_mm
+        *   atomic_inc_not_zero
+        *                                mmput
+        *                                  atomic_dec_and_test
+        *                                exit_oom_victim
+        *                              [...]
+        *                              out_of_memory
+        *                                select_bad_process
+        *                                  # no TIF_MEMDIE task selects new victim
+        *  unmap_page_range # frees some memory
+        */
+       mutex_lock(&oom_lock);
+
        /*
         * Make sure we find the associated mm_struct even when the particular
         * thread has already terminated and cleared its mm.
@@ -457,19 +473,19 @@ static bool __oom_reap_task(struct task_struct *tsk)
         */
        p = find_lock_task_mm(tsk);
        if (!p)
-               return true;
+               goto unlock_oom;
 
        mm = p->mm;
        if (!atomic_inc_not_zero(&mm->mm_users)) {
                task_unlock(p);
-               return true;
+               goto unlock_oom;
        }
 
        task_unlock(p);
 
        if (!down_read_trylock(&mm->mmap_sem)) {
                ret = false;
-               goto out;
+               goto unlock_oom;
        }
 
        tlb_gather_mmu(&tlb, mm, 0, -1);
@@ -511,13 +527,15 @@ static bool __oom_reap_task(struct task_struct *tsk)
         * to release its memory.
         */
        set_bit(MMF_OOM_REAPED, &mm->flags);
-out:
+unlock_oom:
+       mutex_unlock(&oom_lock);
        /*
         * Drop our reference but make sure the mmput slow path is called from a
         * different context because we shouldn't risk we get stuck there and
         * put the oom_reaper out of the way.
         */
-       mmput_async(mm);
+       if (mm)
+               mmput_async(mm);
        return ret;
 }
 
@@ -611,8 +629,6 @@ void try_oom_reaper(struct task_struct *tsk)
 
                        if (!process_shares_mm(p, mm))
                                continue;
-                       if (same_thread_group(p, tsk))
-                               continue;
                        if (fatal_signal_pending(p))
                                continue;