David, could you test with this patch please?
---
>From c4a2a58d3856bc1e528f7c1622a59cef58033cb3 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mho...@suse.com>
Date: Thu, 7 Dec 2017 09:39:03 +0100
Subject: [PATCH] mm, oom_reaper: fix memory corruption
David Rientjes has reported the following memory corruption while the
oom reaper tries to unmap the victims address space
BUG: Bad page map in process oom_reaper pte:6353826300000000 pmd:00000000
addr:00007f50cab1d000 vm_flags:08100073 anon_vma:ffff9eea335603f0 mapping:
(null) index:7f50cab1d
file: (null) fault: (null) mmap: (null) readpage:
(null)
CPU: 2 PID: 1001 Comm: oom_reaper
Call Trace:
[<ffffffffa4bd967d>] dump_stack+0x4d/0x70
[<ffffffffa4a03558>] unmap_page_range+0x1068/0x1130
[<ffffffffa4a2e07f>] __oom_reap_task_mm+0xd5/0x16b
[<ffffffffa4a2e226>] oom_reaper+0xff/0x14c
[<ffffffffa48d6ad1>] kthread+0xc1/0xe0
Tetsuo Handa has noticed that the synchronization inside exit_mmap is
insufficient. We only synchronize with the oom reaper if tsk_is_oom_victim
which is not true if the final __mmput is called from a different context
than the oom victim exit path. This can trivially happen from context of
any task which has grabbed mm reference (e.g. to read /proc/<pid>/ file
which requires mm etc.). The race would look like this
oom_reaper oom_victim task
mmget_not_zero
do_exit
mmput
__oom_reap_task_mm mmput
__mmput
exit_mmap
remove_vma
unmap_page_range
Fix this issue by providing a new mm_is_oom_victim() helper which operates
on the mm struct rather than a task. Any context which operates on a remote
mm struct should use this helper in place of tsk_is_oom_victim. The flag is
set in mark_oom_victim and never cleared so it is stable in the exit_mmap
path.
Reported-by: David Rientjes <rient...@google.com>
Debugged-by: Tetsuo Handa <penguin-ker...@i-love.sakura.ne.jp>
Fixes: 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run
concurrently")
Cc: stable # 4.14
Signed-off-by: Michal Hocko <mho...@suse.com>
---
include/linux/oom.h | 9 +++++++++
include/linux/sched/coredump.h | 5 +++--
mm/mmap.c | 2 +-
mm/oom_kill.c | 4 +++-
4 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 27cd36b762b5..c4139e79771d 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -77,6 +77,15 @@ static inline bool tsk_is_oom_victim(struct task_struct *
tsk)
return tsk->signal->oom_mm;
}
+/*
+ * Use this helper if tsk->mm != mm and the victim mm needs a special
+ * handling. This is guaranteed to stay true after once set.
+ */
+static inline bool mm_is_oom_victim(struct mm_struct *mm)
+{
+ return test_bit(MMF_OOM_VICTIM, &mm->flags);
+}
+
/*
* Checks whether a page fault on the given mm is still reliable.
* This is no longer true if the oom reaper started to reap the
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 9c8847395b5e..da673ca66e7a 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -68,8 +68,9 @@ static inline int get_dumpable(struct mm_struct *mm)
#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */
#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM
killer */
#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */
-#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge
zero page */
-#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */
+#define MMF_OOM_VICTIM 23 /* mm is the oom victim */
+#define MMF_HUGE_ZERO_PAGE 24 /* mm has ever used the global huge
zero page */
+#define MMF_DISABLE_THP 25 /* disable THP for all VMAs */
#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/mm/mmap.c b/mm/mmap.c
index 476e810cf100..d00a06248ef1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3005,7 +3005,7 @@ void exit_mmap(struct mm_struct *mm)
unmap_vmas(&tlb, vma, 0, -1);
set_bit(MMF_OOM_SKIP, &mm->flags);
- if (unlikely(tsk_is_oom_victim(current))) {
+ if (unlikely(mm_is_oom_victim(mm))) {
/*
* Wait for oom_reap_task() to stop working on this
* mm. Because MMF_OOM_SKIP is already set before
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3b0d0fed8480..e4d290b6804b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -666,8 +666,10 @@ static void mark_oom_victim(struct task_struct *tsk)
return;
/* oom_mm is bound to the signal struct life time. */
- if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm))
+ if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
mmgrab(tsk->signal->oom_mm);
+ set_bit(MMF_OOM_VICTIM, &mm->flags);
+ }
/*
* Make sure that the task is woken up from uninterruptible sleep
--
2.15.0
--
Michal Hocko
SUSE Labs
