linux-stable/include/linux/sched/coredump.h
Tetsuo Handa 9bcdeb51bd oom, oom_reaper: do not enqueue same task twice
Arkadiusz reported that enabling memcg's group oom killing causes
strange memcg statistics where there is no task in a memcg despite the
number of tasks in that memcg is not 0.  It turned out that there is a
bug in wake_oom_reaper() which allows enqueuing same task twice which
makes impossible to decrease the number of tasks in that memcg due to a
refcount leak.

This bug existed since the OOM reaper became invokable from
task_will_free_mem(current) path in out_of_memory() in Linux 4.7,

  T1@P1     |T2@P1     |T3@P1     |OOM reaper
  ----------+----------+----------+------------
                                   # Processing an OOM victim in a different memcg domain.
                        try_charge()
                          mem_cgroup_out_of_memory()
                            mutex_lock(&oom_lock)
             try_charge()
               mem_cgroup_out_of_memory()
                 mutex_lock(&oom_lock)
  try_charge()
    mem_cgroup_out_of_memory()
      mutex_lock(&oom_lock)
                            out_of_memory()
                              oom_kill_process(P1)
                                do_send_sig_info(SIGKILL, @P1)
                                mark_oom_victim(T1@P1)
                                wake_oom_reaper(T1@P1) # T1@P1 is enqueued.
                            mutex_unlock(&oom_lock)
                 out_of_memory()
                   mark_oom_victim(T2@P1)
                   wake_oom_reaper(T2@P1) # T2@P1 is enqueued.
                 mutex_unlock(&oom_lock)
      out_of_memory()
        mark_oom_victim(T1@P1)
        wake_oom_reaper(T1@P1) # T1@P1 is enqueued again due to oom_reaper_list == T2@P1 && T1@P1->oom_reaper_list == NULL.
      mutex_unlock(&oom_lock)
                                   # Completed processing an OOM victim in a different memcg domain.
                                   spin_lock(&oom_reaper_lock)
                                   # T1P1 is dequeued.
                                   spin_unlock(&oom_reaper_lock)

but memcg's group oom killing made it easier to trigger this bug by
calling wake_oom_reaper() on the same task from one out_of_memory()
request.

Fix this bug using an approach used by commit 855b018325 ("oom,
oom_reaper: disable oom_reaper for oom_kill_allocating_task").  As a
side effect of this patch, this patch also avoids enqueuing multiple
threads sharing memory via task_will_free_mem(current) path.

Link: http://lkml.kernel.org/r/e865a044-2c10-9858-f4ef-254bc71d6cc2@i-love.sakura.ne.jp
Link: http://lkml.kernel.org/r/5ee34fc6-1485-34f8-8790-903ddabaa809@i-love.sakura.ne.jp
Fixes: af8e15cc85 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: Arkadiusz Miskiewicz <arekm@maven.pl>
Tested-by: Arkadiusz Miskiewicz <arekm@maven.pl>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Aleksa Sarai <asarai@suse.de>
Cc: Jay Kamat <jgkamat@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-02-01 15:46:23 -08:00

80 lines
2.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_COREDUMP_H
#define _LINUX_SCHED_COREDUMP_H
#include <linux/mm_types.h>
#define SUID_DUMP_DISABLE 0 /* No setuid dumping */
#define SUID_DUMP_USER 1 /* Dump as user of process */
#define SUID_DUMP_ROOT 2 /* Dump as root */
/* mm flags */
/* for SUID_DUMP_* above */
#define MMF_DUMPABLE_BITS 2
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
extern void set_dumpable(struct mm_struct *mm, int value);
/*
* This returns the actual value of the suid_dumpable flag. For things
* that are using this for checking for privilege transitions, it must
* test against SUID_DUMP_USER rather than treating it as a boolean
* value.
*/
static inline int __get_dumpable(unsigned long mm_flags)
{
return mm_flags & MMF_DUMPABLE_MASK;
}
static inline int get_dumpable(struct mm_struct *mm)
{
return __get_dumpable(mm->flags);
}
/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ANON_SHARED 3
#define MMF_DUMP_MAPPED_PRIVATE 4
#define MMF_DUMP_MAPPED_SHARED 5
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED 8
#define MMF_DUMP_DAX_PRIVATE 9
#define MMF_DUMP_DAX_SHARED 10
#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS 9
#define MMF_DUMP_FILTER_MASK \
(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\
(1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS)
#else
# define MMF_DUMP_MASK_DEFAULT_ELF 0
#endif
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */
/*
* This one-shot flag is dropped due to necessity of changing exe once again
* on NFS restore
*/
//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */
#define MMF_HAS_UPROBES 19 /* has uprobes */
#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 25 /* mm is the oom victim */
#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */
#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
MMF_DISABLE_THP_MASK)
#endif /* _LINUX_SCHED_COREDUMP_H */