From 4837fe37adff1d159904f0c013471b1ecbcb455e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 14 Dec 2017 15:33:15 -0800 Subject: 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: unmap_page_range+0x1068/0x1130 __oom_reap_task_mm+0xd5/0x16b oom_reaper+0xff/0x14c 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// 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. Debugged by Tetsuo Handa. Link: http://lkml.kernel.org/r/20171210095130.17110-1-mhocko@kernel.org Fixes: 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently") Signed-off-by: Michal Hocko Reported-by: David Rientjes Acked-by: David Rientjes Cc: Tetsuo Handa Cc: Andrea Argangeli Cc: [4.14] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 9 +++++++++ include/linux/sched/coredump.h | 1 + mm/mmap.c | 10 +++++----- mm/oom_kill.c | 4 +++- 4 files changed, 18 insertions(+), 6 deletions(-) diff --git a/include/linux/oom.h b/include/linux/oom.h index 01c91d874a57..5bad038ac012 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -66,6 +66,15 @@ 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..ec912d01126f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -70,6 +70,7 @@ static inline int get_dumpable(struct mm_struct *mm) #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 25 /* mm is the oom victim */ #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 a4d546821214..9efdc021ad22 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3019,20 +3019,20 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ 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 * calling down_read(), oom_reap_task() will not run * on this "mm" post up_write(). * - * tsk_is_oom_victim() cannot be set from under us - * either because current->mm is already set to NULL + * mm_is_oom_victim() cannot be set from under us + * either because victim->mm is already set to NULL * under task_lock before calling mmput and oom_mm is - * set not NULL by the OOM killer only if current->mm + * set not NULL by the OOM killer only if victim->mm * is found not NULL while holding the task_lock. */ + set_bit(MMF_OOM_SKIP, &mm->flags); down_write(&mm->mmap_sem); up_write(&mm->mmap_sem); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c957be32b27a..29f855551efe 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -683,8 +683,10 @@ 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 -- cgit