Re: [PATCH] mm, oom: distinguish blockable mode for mmu notifiers

From: Michal Hocko
Date: Tue Jul 24 2018 - 10:18:19 EST


On Fri 20-07-18 17:09:02, Andrew Morton wrote:
[...]
> - Undocumented return value.
>
> - comment "failed to reap part..." is misleading - sounds like it's
> referring to something which happened in the past, is in fact
> referring to something which might happen in the future.
>
> - fails to call trace_finish_task_reaping() in one case
>
> - code duplication.
>
> - Increases mmap_sem hold time a little by moving
> trace_finish_task_reaping() inside the locked region. So sue me ;)
>
> - Sharing the finish: path means that the trace event won't
> distinguish between the two sources of finishing.
>
> Please take a look?

oom_reap_task_mm should return false when __oom_reap_task_mm return
false. This is what my patch did but it seems this changed by
http://www.ozlabs.org/~akpm/mmotm/broken-out/mm-oom-remove-oom_lock-from-oom_reaper.patch
so that one should be fixed.

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 104ef4a01a55..88657e018714 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -565,7 +565,7 @@ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
/* failed to reap part of the address space. Try again later */
if (!__oom_reap_task_mm(mm)) {
up_read(&mm->mmap_sem);
- return true;
+ return false;
}

pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",


On top of that the proposed cleanup looks as follows:

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 88657e018714..4e185a282b3d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -541,8 +541,16 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
return ret;
}

+/*
+ * Reaps the address space of the give task.
+ *
+ * Returns true on success and false if none or part of the address space
+ * has been reclaimed and the caller should retry later.
+ */
static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
{
+ bool ret = true;
+
if (!down_read_trylock(&mm->mmap_sem)) {
trace_skip_task_reaping(tsk->pid);
return false;
@@ -555,28 +563,28 @@ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
* down_write();up_write() cycle in exit_mmap().
*/
if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
- up_read(&mm->mmap_sem);
trace_skip_task_reaping(tsk->pid);
- return true;
+ goto out_unlock;
}

trace_start_task_reaping(tsk->pid);

/* failed to reap part of the address space. Try again later */
- if (!__oom_reap_task_mm(mm)) {
- up_read(&mm->mmap_sem);
- return false;
- }
+ ret = __oom_reap_task_mm(mm);
+ if (!ret)
+ goto out_finish;

pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
K(get_mm_counter(mm, MM_FILEPAGES)),
K(get_mm_counter(mm, MM_SHMEMPAGES)));
+out_finish:
+ trace_finish_task_reaping(tsk->pid);
+out_unlock:
up_read(&mm->mmap_sem);

- trace_finish_task_reaping(tsk->pid);
- return true;
+ return ret;
}

#define MAX_OOM_REAP_RETRIES 10
--
Michal Hocko
SUSE Labs